Image capture recommendation

The camera and processor of the electronic device compare the subject's posture and the user's posture collection, and generate suggestions and adjustments, solving the problem that the posture does not meet expectations during shooting, and improving the quality and efficiency of the photo.

CN118923123APending Publication Date: 2024-11-08QUALCOMM INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380029422.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-29
Filing Date
2023-03-15
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art is difficult to effectively adjust the posture of the subject being photographed, resulting in the subject not meeting the desired posture when taking the photo, which affects the quality and efficiency of the photo.

Method used

The subject's image is captured by the camera of the electronic device, the posture in the image is compared with the stored user posture set, the recommended adjustments are generated to improve posture matching, and the posture correction is performed using the processor to perform facial detection, image segmentation and machine learning algorithms.

Benefits of technology

The matching degree of subjects' postures was improved, the number of photos was taken was reduced, and the quality and shooting efficiency were improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118923123A_ABST
    Figure CN118923123A_ABST
Patent Text Reader

Abstract

Systems, methods, and non-transitory media are provided for adjusting a posture of a photographed subject. An example method may include obtaining, via a camera of a mobile device, an image depicting a subject in a first pose; determining a match between the first gesture of the subject depicted in the image and a second gesture from a stored set of user gestures; and based on the match, generating a recommendation indicating one or more suggested adjustments to the first gesture of the subject, the one or more suggested adjustments being estimated to increase an amount of match between the first gesture of the subject and the second gesture from the stored set of user gestures.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure as a whole relates to image capture (e.g., capturing one or more photos or videos). For example, aspects of the present disclosure relate to pose-based photo recommendations and / or adjustments, such as adjusting the pose of a photographed subject and recommending pose adjustments to a photographed subject. Background Art

[0002] An increasing number of electronic devices are equipped with camera hardware for capturing images and / or videos for use. For example, a computing device may include a camera (e.g., a mobile device such as a mobile phone or smartphone that includes one or more cameras) to allow the computing device to capture a video or image of a scene, a person, an object, etc. The image or video may be captured and processed by the computing device (e.g., a mobile device, an IP camera, an extended reality device, a connected device, etc.) and stored or output for use (e.g., displayed on the device and / or another device). In some cases, the image or video may be further processed for effects (e.g., compression, image enhancement, image restoration, scaling, frame rate conversion, etc.) and / or certain applications (such as computer vision, extended reality (e.g., augmented reality, virtual reality, etc.), object detection, image recognition (e.g., face recognition, object recognition, scene recognition, etc.), feature extraction, authentication, and automation, etc.). Summary of the invention

[0003] Systems and techniques for adjusting the pose (e.g., posture, position, and / or other attributes) of a photographed subject and / or recommending adjustments to the pose of a photographed subject are described herein. According to at least one example, a method for adjusting the pose of a photographed subject and / or recommending adjustments to the pose of a photographed subject is provided. The method may include: obtaining an image depicting a subject in a first pose via a camera of an electronic device; determining an amount of match between the first pose of the subject depicted in the image and a second pose from a stored set of user poses; and based on the amount of match, generating a recommendation indicating one or more suggested adjustments to the first pose of the subject, the one or more suggested adjustments being estimated to increase the amount of match between the first pose of the subject and the second pose from the stored set of user poses.

[0004] According to at least one example, a non-transitory computer-readable medium for adjusting a posture of a photographed subject and / or recommending an adjustment to the posture of the photographed subject is provided. The non-transitory computer-readable medium may include instructions that, when executed by one or more processors, cause the one or more processors to: obtain an image depicting a subject in a first posture via a camera of an electronic device; determine the amount of match between the first posture of the subject depicted in the image and a second posture from a stored user posture set; and based on the amount of match, generate a recommendation indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase the amount of match between the first posture of the subject and the second posture from the stored user posture set.

[0005] According to at least one example, a device for adjusting the posture of a photographed subject and / or recommending adjustments to the posture of a photographed subject is provided. The device may include a memory and one or more processors coupled to the memory, the one or more processors being configured to: obtain an image depicting a subject in a first posture via a camera of an electronic device; determine an amount of match between the first posture of the subject depicted in the image and a second posture from a stored user posture set; and based on the amount of match, generate a recommendation indicating one or more recommended adjustments to the first posture of the subject, the one or more recommended adjustments being estimated to increase the amount of match between the first posture of the subject and the second posture from the stored user posture set.

[0006] According to at least one example, another device for adjusting the posture of a photographed subject and / or recommending adjustments to the posture of a photographed subject is provided. The device may include components for the following items: obtaining an image depicting a subject in a first posture via a camera of an electronic device; determining an amount of match between the first posture of the subject depicted in the image and a second posture from a stored user posture set; and based on the amount of match, generating a recommendation indicating one or more recommended adjustments to the first posture of the subject, the one or more recommended adjustments being estimated to increase the amount of match between the first posture of the subject and the second posture from the stored user posture set.

[0007] In some aspects, the above-described methods, non-transitory computer-readable media, and devices may: determine a corresponding amount of match between the subject's first posture and each posture from the stored set of user postures; based on the corresponding amount of match between the subject's first posture and each posture from the stored set of user postures, select the second posture from the stored set of user postures, wherein the second posture includes the highest matching posture from the stored set of user postures; and in response to selecting the second posture, generate the recommendation indicating the one or more suggested adjustments to the subject's first posture.

[0008] In some examples, determining the amount of match between the first posture of the subject and the second posture from the stored set of user postures may include comparing the first posture of the subject to the second posture from the stored set of user postures. In some cases, determining the amount of match may include determining a match score for the second posture based on the comparison of the first posture to the second posture.

[0009] In some examples, the match amount indicates the following: an amount of alignment between the first outline of the subject's first posture and the second outline of the second posture, an amount of overlap between the first outline of the subject's first posture and the second outline of the second posture, a measure of similarity between the first outline of the subject's first posture and the second outline of the second posture, and / or a percentage match between the first outline of the subject's first posture and the second outline of the second posture.

[0010] In some aspects, the above-described methods, non-transitory computer-readable media, and devices may: compare the first posture of the subject with each posture from the stored set of user postures; determine a corresponding amount of matching between the first posture of the subject and each posture from the stored set of user postures; and determine a plurality of highest matching postures from the stored set of user postures based on the corresponding amount of matching between the first posture of the subject and each posture from the stored set of user postures, wherein the plurality of highest matching postures include the second posture.

[0011] In some aspects, the above methods, non-transitory computer-readable media, and devices may: generate an indication of the plurality of highest matching gestures; receive user input selecting the second gesture from the plurality of highest matching gestures; and select the second gesture based on the user input.

[0012] In some aspects, the above methods, non-transitory computer-readable media, and apparatus may present the indication of the plurality of highest matching gestures at a display of the electronic device, or transmit the indication of the plurality of highest matching gestures to one or more devices associated with the subject. In some cases, the indication of the plurality of highest matching gestures may include a preview of the plurality of highest matching gestures.

[0013] In some aspects, the above methods, non-transitory computer-readable media, and apparatus may generate the recommendation indicating the one or more suggested adjustments to the first posture of the subject in response to selecting the second posture based on the user input.

[0014] In some cases, generating the recommendation indicating the one or more suggested adjustments to the first posture of the subject may include: determining one or more differences between the first posture of the subject and the second posture from the stored set of user postures based on a comparison between the first posture of the subject and the second posture from the stored set of user postures; and determining the one or more suggested adjustments based on the one or more differences between the first posture of the subject and the second posture from the stored set of user postures.

[0015] In some aspects, the above-described methods, non-transitory computer-readable media, and apparatus may: obtain, via the camera of the electronic device, a second image depicting the subject in a third posture; detect the third posture of the subject in the second image; and determine that the third posture of the subject at least partially includes the one or more suggested adjustments.

[0016] In some aspects, the above methods, non-transitory computer-readable media, and apparatus may, in response to determining that the third posture of the subject includes the one or more suggested adjustments, transmit the second image depicting the subject in the third posture to one or more devices associated with the subject. In some aspects, the above methods, non-transitory computer-readable media, and apparatus may, in response to determining that the third posture of the subject includes the one or more suggested adjustments, store the second image depicting the subject in the third posture.

[0017] In some aspects, the above-described methods, non-transitory computer-readable media, and devices may: determine one or more differences between the third posture of the subject and the second posture from the stored set of user postures based on a comparison between the third posture of the subject and the second posture from the stored set of user postures; determine one or more additional adjustments based on the one or more differences between the third posture of the subject and the second posture from the stored set of user postures; and modify the second image based on the one or more additional adjustments using a machine learning model.

[0018] In some examples, modifying the second image based on the one or more additional adjustments may include performing at least one of a geometric transformation of at least a portion of the third posture in the second image associated with the one or more additional adjustments and a transformation of a set of pixel coordinates in the second image that corresponds to pixels depicting at least the portion of the third posture in the second image associated with the one or more additional adjustments.

[0019] In some aspects, the above methods, non-transitory computer-readable media, and apparatus may update the stored set of user gestures to include a particular gesture of the subject depicted in one or more images of the subject.

[0020] In some aspects, the above-described methods, non-transitory computer-readable media, and apparatus may: determine that the subject is facing a display of the electronic device; and present the recommendation indicating one or more suggested adjustments to the first posture of the subject at the display of the electronic device, the recommendation being presented at the display when the subject is facing the display.

[0021] In some aspects, the above methods, non-transitory computer-readable media, and apparatus may present the recommendation indicating one or more suggested adjustments to the first posture of the subject at a first portion of a foldable display of the electronic device. In some examples, the first portion of the foldable display may include a display portion that is at least partially folded relative to a second portion of the foldable display.

[0022] In some aspects, the above-described methods, non-transitory computer-readable media, and devices may generate tactile feedback based on the one or more suggested adjustments to the first posture of the subject, the tactile feedback comprising a vibration indicative of at least one suggested adjustment from the one or more suggested adjustments.

[0023] In some aspects, the above methods, non-transitory computer-readable media, and apparatus may transmit the one or more suggested adjustments to a device associated with the subject. In some examples, the device may include a watch, a head-mounted display, a mobile phone, and / or glasses.

[0024] In some aspects, each of the devices described above is a mobile device, a smart or connected device, a camera system, and / or an extended reality (XR) device (e.g., a virtual reality (VR) device, an augmented reality (AR) device, or a mixed reality (MR) device), or may be part of or may include these devices. In some examples, the device may include a mobile device (e.g., a mobile phone or so-called "smart phone" or other mobile device), a wearable device, a personal computer, a laptop computer, a tablet computer, a server computer, a robotic device or system, or other device, or may be part of these devices. In some aspects, the device includes an image sensor (e.g., a camera) or multiple image sensors (e.g., multiple cameras) for capturing one or more images. In some aspects, the device includes one or more displays for displaying one or more images, notifications, and / or other displayable data. In some aspects, the device includes one or more speakers, one or more light-emitting devices, and / or one or more microphones. In some aspects, the device described above may include one or more sensors. In some cases, the one or more sensors may be used to determine the location of the device, the state of the device (e.g., tracking state, operating state, temperature, humidity level, and / or another state) and / or for other purposes.

[0025] This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used in isolation to determine the scope of the claimed subject matter. The subject matter should be understood by reference to appropriate portions of the entire specification of this patent, any or all drawings, and each claim.

[0026] The foregoing and other features and embodiments will become more apparent upon reference to the following description, claims and accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Illustrative examples of the present application are described in detail below with reference to the following drawings:

[0028] Figure 1 is a diagram illustrating an example of an electronic device for adjusting user pose settings in a photograph and / or providing feedback and recommendations for adjusting the pose of a photographed subject according to some examples of the present disclosure;

[0029] Figure 2A is a diagram illustrating an example preview image of a subject photographed by an electronic device and a segmentation mask generated based on the preview image according to some examples of the present disclosure;

[0030] Figure 2B is a diagram illustrating example preview images of a group of subjects photographed by an electronic device and segmentation masks generated based on the preview images according to some examples of the present disclosure;

[0031] Figure 3 is a diagram illustrating an example implementation of gesture modes according to some examples of the present disclosure;

[0032] Figure 4 is a diagram illustrating another example implementation of a gesture mode according to some examples of the present disclosure;

[0033] Figure 5 is a flow chart illustrating an example process for implementing gesture mode according to some examples of the present disclosure;

[0034] Figure 6 is a diagram illustrating an example of automatic posture correction performed as part of a gesture mode of an electronic device according to some examples of the present disclosure;

[0035] Figure 7 is a flow chart illustrating an example process for performing automatic gesture correction as part of a gesture mode of an electronic device according to some examples of the present disclosure;

[0036] Fig. 8A is a flow chart illustrating an example process for determining a subject's photographing pose according to some examples of the present disclosure;

[0037] Figure 8B is a flow chart illustrating another example process for determining a subject's photographing pose according to some examples of the present disclosure;

[0038] Fig. 9 are diagrams illustrating example posture adjustments of photographed subjects according to some examples of the present disclosure;

[0039] Fig.10 is a diagram illustrating an example of a specific implementation of a gesture pattern for verifying or adjusting user movement associated with an activity according to some examples of the present disclosure;

[0040] Fig.11 is a flow chart illustrating an example process for adjusting camera settings based on event data according to some examples of the present disclosure; and

[0041] Fig.12 An example computing device architecture according to some examples of the present disclosure is illustrated. DETAILED DESCRIPTION

[0042] Some aspects and embodiments of the present disclosure are provided below. Some of these aspects and embodiments can be applied independently, and some of them can be applied in combination, which is obvious to those skilled in the art. In the following description, specific details are set forth for explanation purposes in order to provide a thorough understanding of each embodiment of the application. However, it will be apparent that each embodiment can be put into practice without these specific details. Each drawing and description are not intended to be restrictive.

[0043] The following description only provides example embodiments and is not intended to limit the scope, applicability or configuration of the present disclosure. On the contrary, the following description of the exemplary embodiments will provide an enabling description for implementing the exemplary embodiments to those skilled in the art. It should be understood that various changes may be made to the function and arrangement of elements without departing from the essence and scope of the present application as set forth in the appended claims.

[0044] An electronic device (e.g., a mobile phone, a wearable device (e.g., a smart watch, smart glasses, etc.), a tablet computer, an extended reality (XR) device (e.g., a virtual reality (VR) device, an augmented reality (AR) device, a mixed reality (MR) device, etc.), a connected device, a laptop computer, etc.) may implement a camera to capture images or video frames of scenes, people, animals, and / or any object. A camera may refer to a device that uses an image sensor to receive light and capture an image frame (such as a still image or a video frame). The terms "image," "image frame," and "frame" are used interchangeably herein. A camera system may include a processor (e.g., an image signal processor (ISP), etc.) that may receive one or more images and process the one or more images. For example, a raw image captured by a camera sensor may be processed by an ISP to generate a final image. The processing performed by the ISP may be performed by filters or processing blocks applied to the captured image, such as denoising or noise filtering, edge enhancement, color balance, contrast, intensity adjustment (such as darkening or lightening), hue adjustment, etc. Image processing blocks or modules may include lens / sensor noise correction, Bayer filters, demosaicing, color conversion, correction or enhancement / suppression of image properties, denoising filters, sharpening filters, etc.

[0045] Users often use electronic devices equipped with cameras to capture their own images or capture group photos depicting a group of people. In many cases, users (or user groups) like to pose in specific positions and / or angles when taking images of themselves in a desired posture. However, when users (or user groups) take photos of themselves, the photos usually do not depict the users in the postures they expect. In some examples, this may occur because the person taking the photos is unskilled or has no experience in taking photos and / or because the photos are captured when the user being photographed is not in the desired posture. In many cases, users can take multiple photos to obtain photos depicting users in desired postures.

[0046] In addition, when taking a group photo, some (or all) of the people in the group photo may appear to be in different or inconsistent postures. Because the postures of the people in the photos are different or inconsistent, the resulting photo may not look as expected by some or all of the people in the photo. Therefore, the group of people may take multiple photos together until they capture a photo depicting the group of people (and / or each person in the group) in the desired posture and / or until they capture a photo they like. This may be time consuming and may result in capturing a large number of unnecessary photos. It may also be difficult to obtain a photo depicting the group of people (and / or each person in the group) in the desired posture. In many cases, the group of people may not be able to obtain a photo depicting the group in a desired posture or set of postures.

[0047] Described herein are systems, apparatus, methods (also referred to as processes), and computer-readable media (collectively referred to herein as "systems and techniques") for adjusting the pose of a photographed subject and / or recommending adjustments to the pose of a photographed subject. As used herein, a pose may refer to a user's posture, position, and / or other attributes. In some examples, a camera device of an electronic device (e.g., an XR device, a mobile device, a tablet computer, a camera system, a connected device, a laptop computer, a smart wearable device, etc.) may implement a pose mode to adjust the pose of a subject photographed using the camera device and / or provide feedback to the subject on how to adjust the subject's pose to match a specific pose from a set of user poses stored on the electronic device. In some aspects, when the electronic device detects one or more faces in a preview image of the subject, the electronic device may perform facial detection on the preview image and automatically enable a pose mode on the camera device of the electronic device (or generate a recommendation to enable a pose mode on the camera device).

[0048] The user pose collection may include previous poses of the subject depicted in previous photographs of the subject, professional poses (e.g., poses of the subject from photographs taken by one or more professional photographers, poses of the subject in professional photographs, poses of a specific subject from professional photographs, poses from pose templates, etc.), a collection of stick figures in specific poses (e.g., stick figures depicting specific poses), and / or any other user pose collection. The electronic device may store the user pose collection for use in portrait mode as described herein. In some examples, the electronic device may store each pose selected by the subject when taking a photograph and / or each pose of the subject depicted in a photograph taken by the subject / photo of the subject taken.

[0049] In some cases, the electronic device may compare the pose of the subject in the preview image captured by the camera device of the electronic device with the user pose set in the storage device. Based on the comparison, the electronic device may identify the pose with the highest match to the pose of the subject in the preview image from the user pose set. Then, the electronic device may adjust the pose of the subject to match (or substantially match) the identified pose from the user pose set and / or provide the subject with a recommendation for adjusting the pose of the subject to match (or substantially match) the identified pose from the user pose set. In other examples, the electronic device may identify the top n highest matching poses from the user pose set based on the comparison. For example, the electronic device may compare the pose of the subject in the preview image with the user pose set and determine a score for each user pose in the user pose set. Each score may reflect the amount of match between the corresponding pose from the user pose set and the pose of the subject in the preview image. The electronic device may select the pose with the top n scores from the user pose set. The electronic device may allow the subject to select one of these postures and use the selected posture to adjust the subject's posture to match (or substantially match) the selected posture and / or provide the subject with a recommendation for adjusting the subject's posture to match (or substantially match) the selected posture.

[0050] In some cases, the electronic device may present a user pose set to the subject and allow the subject to select a specific pose from the user pose set. The electronic device may compare the specific pose selected by the subject with the pose of the subject depicted in the preview image captured by the camera device of the electronic device. The electronic device may use the difference between the specific pose selected by the subject and the pose of the subject depicted in the preview image to adjust the pose of the subject to match (or substantially match) the specific pose selected by the subject and / or provide the subject with a recommendation for adjusting the pose of the subject to match (or substantially match) the specific pose selected by the subject. For example, the electronic device may allow the subject to select a specific pose from the user pose set. The electronic device may determine any difference between the specific pose and the pose of the subject in the preview image of the subject captured by the camera device of the electronic device, and use the determined difference between the specific pose and the pose of the subject in the preview image of the subject to provide the subject with a recommendation for adjusting the pose of the subject to match (or substantially match) the specific pose and / or guide the subject to achieve a pose matching (or substantially matching) the specific pose.

[0051] In some cases, the electronic device may perform image segmentation to generate a segmentation mask corresponding to the body shape and posture of the subject, as depicted in a preview image of the subject captured by a camera device of the electronic device. The electronic device may compare the segmentation mask with a user pose set (e.g., a user pose representation or stick figure depicted in a specific pose) to determine the amount of match between the subject's pose depicted in the preview image of the subject and one or more poses in the user pose set. In some examples, the electronic device may recommend a pose adjustment to the subject based on the highest matching pose in the user pose set. In some examples, the electronic device may provide feedback to the subject to adjust the subject's pose to match (or substantially match) the highest matching pose from the user pose set. In some cases, the electronic device may provide feedback to the subject to make a pose adjustment based on the difference between the subject's pose depicted in the preview image and the highest matching pose from the user pose set. The electronic device may provide feedback to the subject by displaying a pose adjustment recommendation or transmitting (e.g., via wired or wireless communication) feedback to another device (such as a mobile device of the subject). In some cases, the electronic device may provide feedback to the subject and a depiction of the highest matching pose from the user pose set.

[0052] In some aspects, the electronic device may perform automatic posture correction to adjust the posture of the subject depicted in the preview frame according to the selected posture from the user posture set. For example, the electronic device may perform image segmentation to determine the posture of the subject in the preview image. The electronic device may compare the posture of the subject with the selected posture from the user posture set. Then, the electronic device may adjust the posture of the subject to better match the selected posture from the user posture set. In some examples, the electronic device may implement a machine learning algorithm to automatically align the posture of the subject to the outline (e.g., boundary shape, such as a bounding box) of the selected posture from the user posture set. In some cases, the electronic device may implement an algorithm / model, such as, for example, but not limited to, a PoseNet posture estimation model, a scale-invariant feature transform (SIFT) algorithm, a posture detection algorithm, a speeded-up robust feature (SURF) algorithm, an orientation FAST and rotation BRIEF (ORB) algorithm, and / or any posture detection algorithm / model, or a combination of posture detection algorithms / models.

[0053] Various aspects of the application will be described with reference to the accompanying drawings.

[0054] Figure 1 is a diagram illustrating an example of an electronic device 100 for adjusting user pose settings in a photograph and / or providing feedback / recommendations for adjusting the pose of a photographed subject, as further described herein. In some examples, the electronic device 100 may include an electronic device configured to implement a pose mode as described herein. In some aspects, the electronic device 100 may be configured to provide one or more functionalities, such as, for example, imaging functionality, image data segmentation functionality, detection functionality (e.g., object detection, pose detection, face detection, shape detection, scene detection, etc.), image processing functionality, extended reality (XR) functionality (e.g., positioning / tracking, detection, classification, mapping, content reproduction, etc.), device management and / or control functionality, gaming functionality, computer vision, robotics functionality, automation, and / or any other computing functionality.

[0055] exist Figure 1In the illustrative example shown, the electronic device 100 may include one or more camera devices (such as camera 102 and camera 104), one or more sensors 106 (e.g., an ultrasonic sensor, an inertial measurement unit, a depth sensor using any suitable technology for determining depth (e.g., based on time of flight (ToF), structured light, or other depth sensing technology or system), a touch sensor, a microphone, etc.), a storage device 108, and one or more computing components 110. In some cases, the electronic device 100 may optionally include one or more other / additional sensors, such as, for example, but not limited to, a pressure sensor (e.g., an atmospheric pressure sensor and / or any other pressure sensor), a gyroscope, an accelerometer, a magnetometer, and / or any other sensor. In some examples, the electronic device 100 may include additional components, such as, for example, a light emitting diode (LED) device, a cache, a communication interface, a display, a memory device, etc. The following description with respect to Fig.12 An example architecture and example hardware components that may be implemented by electronic device 100 are further described.

[0056] The electronic device 100 may be part of or implemented by a single computing device or multiple computing devices. In some examples, the electronic device 100 may be part of an electronic device (or multiple electronic devices), such as a camera system (e.g., a digital camera, an IP camera, a video camera, a security camera, etc.), a phone system (e.g., a smart phone, a cellular phone, a conference system, etc.), a laptop or notebook computer, a tablet computer, a set-top box, a smart TV, a display device, a game console, an XR device (such as an HMD), an IoT (Internet of Things) device, a smart wearable device, or any other suitable electronic device.

[0057] In some implementations, the camera 102, the camera 104, the one or more sensors 106, the storage device 108, and / or the one or more computing components 110 may be part of the same computing device. For example, in some cases, the camera 102, the camera 104, the one or more sensors 106, the storage device 108, and / or the one or more computing components 110 may be integrated with or integrated into a camera system, a smart phone, a laptop, a tablet computer, a smart wearable device, an XR device such as an HMD, an IoT device, a gaming system, and / or any other computing device. In other implementations, the camera 102, the camera 104, the one or more sensors 106, the storage device 108, and / or the one or more computing components 110 may be part of or implemented by two or more separate computing devices.

[0058] By way of example and not limitation, one or more computing components 110 of the electronic device 100 may include a central processing unit (CPU) 112, a graphics processing unit (GPU) 114, a digital signal processor (DSP) 116, and / or an image signal processor (ISP) 118. In some examples, the electronic device 100 may include other processors or processing devices, such as, for example, a computer vision (CV) processor, a neural network processor (NNP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc. The electronic device 100 may use one or more computing components 110 to perform various computing operations, such as, for example, gesture mode functionality as described herein, extended reality operations (e.g., tracking, localization, object detection, classification, pose estimation, mapping, content anchoring, content presentation, etc.), detection (e.g., face detection, object detection, scene detection, human detection, etc.), image segmentation, automatic gesture correction, device control operations, image / video processing, graphics presentation, machine learning, data processing, modeling, computing, computer vision, and / or any other operations.

[0059] In some cases, one or more computing components 110 may include other electronic circuitry or hardware, computer software, firmware, or any combination thereof to perform any of the various operations described herein. In some examples, one or more computing components 110 may include more than Figure 1 The computing components shown in FIG. 1 may be more or less than the computing components shown in FIG. 11. In addition, CPU 112, GPU 114, DSP 116, and ISP 118 are merely illustrative examples of computing components provided for illustration purposes.

[0060] Camera 102 and / or camera 104 may include any image and / or video sensor and / or image / video capture device, such as a digital camera sensor, a video camera sensor, a smart phone camera sensor, an image / video capture device on an electronic device (such as a television or computer, camera), etc. In some cases, camera 102 and / or camera 104 may be part of a camera system or computing device (such as a digital camera, a video camera, an IP camera, a smart phone, a smart TV, a gaming system, etc. In addition, in some cases, camera 102 and camera 104 may include multiple image sensors, such as a rear sensor device and a front sensor device, and may be part of a dual camera or other multi-camera assembly (e.g., including two cameras, three cameras, four cameras, or other number of cameras). In some examples, camera 102 and / or camera 104 may be part of a camera. The camera may be configured to implement a gesture mode as further described herein.

[0061] In some examples, cameras 102 and 104 may capture image data and generate frames based on the image data and / or provide the image data or frames to one or more computing components 110 for processing. A frame may include a video frame or a static image in a video sequence. A frame may include an array of pixels representing a scene. For example, a frame may be: a red-green-blue (RGB) frame having red, green, and blue color components per pixel; a luminance, redness, blueness (YCbCr) frame having a luminance component and two chrominance (color) components (redness and blueness) per pixel; or any other suitable type of color or monochrome picture.

[0062] Storage 108 may include any storage device for storing data such as, for example, but not limited to, image data, gesture data, scene data, user data, preferences, etc. Storage 108 may store data from any component of electronic device 100. For example, storage 108 may store data or measurements from any of cameras 102 and 104, one or more sensors 106, computing component 110 (e.g., processing parameters, outputs, videos, images, segmentation maps / masks, depth maps, filtering results, computational results, detection results, gesture correction data, etc.), gesture pattern engine 120, and / or any other component. In some examples, storage 108 may include a buffer to store data processed by computing component 110 (e.g., image data, gesture data, etc.).

[0063] The one or more computing components 110 may use data from the camera 102, the camera 104, the one or more sensors 106, the storage 108, and / or any other sensors and / or components to perform image / video processing, gesture mode functionality as described herein, automatic gesture correction as described herein, machine learning, XR processing, device management / control, detection (e.g., object detection, face detection, scene detection, human detection, etc.), and / or other operations as described herein. In some examples, the one or more computing components 110 may implement one or more software engines and / or algorithms, such as, for example, the gesture model engine 120 or algorithms as described herein. In some cases, the one or more computing components 110 may implement one or more other and / or additional components and / or algorithms, such as a machine learning model, a computer vision algorithm, a neural network, and / or any other algorithm and / or component.

[0064] The gesture mode engine 120 may implement one or more algorithms and / or machine learning models configured to implement gesture modes and / or any of the gesture mode operations described herein. In some examples, the gesture mode engine 120 may be configured to adjust the posture of a subject photographed by the electronic device 100 (e.g., via the camera 102 or the camera 104) and / or recommend adjustments to the posture of the photographed subject. In some examples, the gesture mode engine 120 may be configured to generate and / or provide feedback to the subject on how to adjust the subject's posture to match a specific posture from the user gesture set stored on the storage device 108. In some aspects, when the gesture mode engine 120 detects one or more faces in the preview image, the gesture mode engine may perform facial detection on the preview image of the subject and automatically enable the gesture mode on the camera 102 and / or the camera 104 (or generate a recommendation to enable the gesture mode on the camera 102 and / or the camera 104).

[0065] The user pose collection may include previous poses of a subject depicted in previous photographs of the subject, professional poses (e.g., poses of a subject from photographs taken by one or more professional photographers, poses of a subject in professional photographs, poses of a specific subject from professional photographs, poses from pose templates, etc.), a collection of stick figures in specific poses (e.g., stick figures depicting specific poses), poses from images in a photo library in electronic device 100, poses from images in a photo library of another device, poses from images in a photo sharing and / or storage service (e.g., a cloud-based photo sharing and / or storage service, etc.), and / or any other user pose collection.

[0066] In some cases, gesture mode engine 120 may convert a photo (e.g., from a photo library of electronic device 100, a photo library of another device, a photo from a photo sharing and / or storage service, etc.) into a stick figure depicting a selected gesture (e.g., a gesture stick figure) and store the stick figure as part of a user gesture collection. Gesture mode engine 120 may store the user gesture collection on storage device 108 for use in portrait mode as described herein. In some examples, gesture mode engine 120 may store each gesture selected by the subject when the photo was taken and / or each gesture of the subject depicted in a photo taken by the subject / photo taken of the subject on storage device 108.

[0067] In some examples, gesture pattern engine 120 may learn (e.g., using a machine learning model or any learning algorithm) the gesture preferences of one or more users. For example, when a user takes a photo in a particular pose or accepts a recommended photo pose, gesture pattern engine 120 may add the particular and / or recommended pose to the user's gesture collection. In some examples, gesture pattern engine 120 may identify one or more characteristics of each pose used by a user and / or accepted by a user, and use the one or more characteristics to help identify poses of interest for future photos and / or recommend adjustments to poses in the captured photo.

[0068] In some cases, gesture pattern engine 120 may compare a subject's gesture in a preview image captured by electronic device 100 (e.g., via camera 102 or camera 104) with a set of user gestures in storage device 108. Based on the comparison, gesture pattern engine 120 may identify a gesture from the set of user gestures that has the highest match to the subject's gesture in the preview image. Then, gesture pattern engine 120 may adjust the subject's gesture to match (or substantially match) the identified gesture from the set of user gestures and / or provide the subject with a recommendation for adjusting the subject's gesture to match (or substantially match) the identified gesture from the set of user gestures. In other examples, gesture pattern engine 120 may identify the top n highest matching gestures from the set of user gestures based on the comparison. For example, gesture pattern engine 120 may compare the subject's gesture in the preview image with the set of user gestures and determine a score for each user gesture in the set of user gestures. Each score may reflect the amount of match between a corresponding gesture from the set of user gestures and the subject's gesture in the preview image. Gesture pattern engine 120 may select gestures with the top n scores from the set of user gestures. In some cases, posture mode engine 120 may allow the subject to select one of these postures and use the selected posture to adjust the subject's posture to match (or substantially match) the selected posture and / or provide the subject with a recommendation for adjusting the subject's posture to match (or substantially match) the selected posture.

[0069] In some cases, the gesture pattern engine 120 may present a user gesture set to the subject (e.g., on a display device of the electronic device 100 and / or a display device of a separate electronic device) and allow the subject to select a specific gesture from the user gesture set. The specific gesture selected by the subject may represent a gesture that the subject wishes to match in a photo of the subject. The gesture pattern engine 120 may compare the specific gesture selected by the subject with the subject's gesture depicted in a preview image captured by the electronic device 100. The gesture pattern engine 120 may use the difference between the specific gesture selected by the subject and the subject's gesture depicted in the preview image to adjust the subject's gesture to match (or substantially match) the specific gesture selected by the subject and / or provide the subject with a recommendation for adjusting the subject's gesture to match (or substantially match) the specific gesture selected by the subject. For example, the gesture pattern engine 120 may allow the subject to select a specific gesture from the user gesture set. Posture pattern engine 120 may determine any differences between a particular posture and a posture of a subject in a preview image of the subject captured by electronic device 100, and use the determined differences between the particular posture and the posture of the subject in the preview image of the subject to provide the subject with a recommendation for adjusting the subject's posture to match (or substantially match) the particular posture and / or to guide the subject to achieve a posture that matches (or substantially matches) the particular posture.

[0070] In some cases, gesture pattern engine 120 may perform image segmentation to generate a segmentation mask corresponding to the subject's body shape and posture, as depicted in a preview image of the subject captured by electronic device 100. Gesture pattern engine 120 may compare the segmentation mask to a user gesture set (e.g., a user gesture representation or stick figure depicted in a particular gesture) to determine an amount of match between the subject's gesture depicted in the preview image of the subject and one or more gestures in the user gesture set. In some examples, gesture pattern engine 120 may recommend a gesture adjustment to the subject based on the highest matching gesture in the user gesture set. In some examples, gesture pattern engine 120 may provide feedback to the subject to adjust the subject's gesture to match (or substantially match) the highest matching gesture from the user gesture set.

[0071] In some cases, gesture pattern engine 120 may provide feedback for gesture adjustments based on the difference between the subject's gesture depicted in the preview image and the highest matching gesture from the user gesture set. Gesture pattern engine 120 may provide feedback to the subject by displaying (e.g., via a display device of electronic device 100) gesture adjustment recommendations or transmitting (e.g., via wired or wireless communication) feedback to another device (e.g., a mobile device of the subject). In some cases, gesture pattern engine 120 may provide feedback to the subject along with a depiction of the highest matching gesture from the user gesture set.

[0072] In some aspects, the posture mode engine 120 may perform automatic posture correction to adjust the posture of the subject depicted in the image or preview image according to the selected posture from the user posture set. For example, the posture mode engine 120 may perform image segmentation to determine the posture of the subject in the image or preview image. The posture mode engine 120 may compare the posture of the subject with the selected posture from the user posture set. Then, the posture mode engine 120 may adjust the posture of the subject to better match the selected posture from the user posture set. In some examples, the posture mode engine 120 may implement a machine learning algorithm to automatically align the posture of the subject to the outline (e.g., a bounding shape, such as a bounding box) of the selected posture from the user posture set. In some cases, the posture mode engine 120 may implement an algorithm / model, such as, for example, but not limited to, a PoseNet posture estimation model, a scale-invariant feature transform (SIFT) algorithm, a posture detection algorithm, a speeded-up robust feature (SURF) algorithm, an orientation FAST and rotation BRIEF (ORB) algorithm, a neural network configured to perform one or more operations as described herein, and / or any posture detection algorithm / model, or a combination of posture detection algorithms / models.

[0073] In some cases, one or more sensors 106 may detect acceleration, angular velocity, and / or orientation of the electronic device 100 and generate measurements based on the detected acceleration. In some cases, one or more sensors 106 may detect and measure the orientation, linear velocity, and / or angular velocity of the electronic device 100. For example, one or more sensors 106 may measure the movement and / or pitch, roll, and yaw of the electronic device 100. In some examples, the electronic device 100 may use measurements obtained by one or more sensors 106 and / or data from one or more of the cameras 102 and / or the cameras 104 to calculate the posture of the electronic device 100 in a three-dimensional (3D) space. In some cases, the electronic device 100 may additionally or alternatively use sensor data from the camera 102, the camera 104, one or more sensors 106, and / or any other sensor to perform tracking, posture estimation, mapping, image segmentation, facial detection, human detection, scene detection, object detection, image data pre-processing and / or post-processing, and / or other operations as described herein.

[0074] Figure 1 The components shown in FIG. 1 and FIG. 2 are illustrative examples provided for illustration purposes. In other examples, the electronic device 100 may include Figure 1 Although electronic device 100 is shown as including certain components, those skilled in the art will appreciate that electronic device 100 may include more or fewer components than those shown in FIG. Figure 1For example, in some instances, electronic device 100 may include one or more memory devices (e.g., RAM, ROM, cache, etc.), one or more networking interfaces (e.g., wired and / or wireless communication interfaces, etc.), one or more display devices, caches, storage devices, and / or Figure 1 Other hardware or processing devices not shown. Fig.12 Illustrative examples of computing devices and / or hardware components that may be implemented using electronic device 100 are described.

[0075] Figure 2A 2 is a diagram illustrating an example preview image 202 of a subject 204 photographed by an electronic device 100 and a segmentation mask 212 generated based on the preview image 202. The preview image 202 shows the subject 204 posing for a photo in a specific pose. The electronic device 100 may perform image segmentation on the preview image 202 to generate the segmentation mask 212. The segmentation mask 212 depicts a mask of the subject 204 and reflects the body shape and specific pose of the subject depicted in the preview image 202. In some examples, the electronic device 100 may generate a preview image 210 that depicts the segmentation mask 212 in the scene of the preview image 202. In some cases, the electronic device 100 may display the preview image 210 depicting the segmentation mask 212 for preview by the subject, and / or may transmit the preview image 210 to another electronic device, such as a mobile device of the subject.

[0076] The electronic device 100 may use the segmentation mask 212 to determine whether a particular posture of the subject 204 as depicted in the preview image 202 matches (or substantially matches) any posture from the user posture set stored at the electronic device 100. In some cases, the electronic device 100 may compare the segmentation mask 212 with the user posture set stored at the electronic device 100, and determine a corresponding score of the corresponding posture from the user posture set based on the comparison. For example, the electronic device 100 may compare the outline of the segmentation mask 212 with the outline of the user posture set to determine the score of the user posture set based on the matching result. The corresponding score may indicate the degree and / or goodness of the corresponding posture matching the segmentation mask 212. For example, the score determined for the corresponding posture may increase as the matching between the corresponding posture and the segmentation mask 212 increases, and may decrease as the matching between the corresponding posture and the segmentation mask 212 decreases.

[0077] In some cases, the electronic device 100 may recommend to the subject the posture with the highest score from the user posture set, or the first n postures with the top n scores. Then, the electronic device 100 may assist the subject in achieving the posture with the highest score or the posture selected by the subject from the recommended postures. For example, the electronic device 100 may generate feedback for the subject to help or guide the subject to achieve the posture with the highest score or the posture selected by the subject. In some cases, the electronic device 100 may generate feedback when the subject poses for the photo and try to achieve a posture that matches (or substantially matches) the posture with the highest score or the posture selected by the subject. For illustration, the electronic device 100 may generate feedback for the subject indicating that the subject should adjust the subject's posture in a specific way or move one or more body parts in a specific way to better match the posture with the highest score or the posture selected by the subject.

[0078] Figure 2B 2 is a diagram illustrating an example preview image 222 of a group of subjects 230-238 photographed by electronic device 100 and segmentation masks 242-250 generated based on preview image 222. Preview image 222 shows subjects 230-238 in the group posing for a photo in a specific pose. Electronic device 100 may perform image segmentation on preview image 222 to generate segmentation masks 242-250. Segmentation masks 242-250 depict masks of subjects 230-238 and reflect the body shape and specific pose of the subjects depicted in preview image 222. In some examples, electronic device 100 may generate preview image 240 that depicts segmentation masks 242-250 in the scene of preview image 222. In some cases, electronic device 100 may display preview image 240 depicting segmentation masks 242-250 for preview by one or more of subjects 230-238, and / or may transmit preview image 240 to one or more other electronic devices, such as one or more mobile devices of one or more of subjects 230-238.

[0079] The electronic device 100 may use the segmentation masks 242-250 to determine whether any of the specific postures of the subjects 230-238 as depicted in the preview image 222 matches (or substantially matches) any posture from the user gesture set stored at the electronic device 100. In some cases, the electronic device 100 may compare the segmentation masks 242-250 with the user gesture set stored at the electronic device 100, and determine the corresponding score of the corresponding posture from the user gesture set based on the comparison. For example, the electronic device 100 may compare the outline of each segmentation mask in the segmentation masks 242-250 with the outline of the user gesture set to determine the score of the user gesture set based on the matching result. The corresponding score may indicate the degree and / or goodness of the corresponding posture matching the segmentation masks 242-250. For example, the score determined for the corresponding posture may increase as the matching between the corresponding posture and the segmentation mask from the segmentation mask 242-250 increases, and may decrease as the matching between the corresponding posture and the segmentation mask from the segmentation mask 242-250 decreases.

[0080] like Figure 2B As shown, segmentation masks 242-250 depict changes between the poses of subjects 230-238. For example, segmentation mask 244 and segmentation mask 250 show that subjects 232 and 238 have different standing positions than subjects 230, 234, and 236. In some cases, subjects 230-238 may want to have similar poses in the group photo or one or more poses that are different from the poses shown in preview image 222. Electronic device 100 can use segmentation masks 242-250 and the user pose set in the storage device to adjust one or more poses of one or more of subjects 230-238, or provide feedback to help subjects 230-238 pose in a manner that matches (or substantially matches) one or more poses from the user pose set in the memory.

[0081] In some cases, the electronic device 100 may recommend the pose with the highest score from the user pose set, or the first n poses with the top n scores to the subjects 230-238. The electronic device 100 may assist the subjects 230-238 in achieving the pose with the highest score or one or more poses selected from the recommended poses by one or more of the subjects 230-238. For example, the electronic device 100 may generate feedback for one or more of the subjects 230-238 to help or guide one or more subjects to achieve the pose with the highest score or one or more poses selected by one or more subjects. In some cases, the electronic device 100 may generate feedback when the subjects 230-238 pose for the group photo and try to achieve a pose that matches (or substantially matches) the pose with the highest score or one or more poses selected by one or more subjects. For illustration, the electronic device 100 may generate feedback for the subjects 230-238 indicating that one or more of the subjects 230-238 should adjust their poses in a specific way or move one or more body parts in a specific way, so as to better match the pose with the highest score or one or more poses selected by one or more subjects.

[0082] Figure 3 is a diagram illustrating an example implementation of a gesture mode. In some examples, when electronic device 100 detects a subject's face in a preview image, the electronic device may automatically enable gesture mode. For example, when electronic device 100 generates a preview image of a subject, electronic device 100 may perform face detection on the preview image and automatically enable gesture mode when a face is detected in the preview image. In other examples, a user of electronic device 100 may manually enable gesture mode from a camera application or device controls or settings.

[0083] When electronic device 100 is in gesture mode, a user (e.g., subject 306 or a user of electronic device 100) may select a photo pose for subject 306 from user pose set 302. For example, subject 306 may select a pose that subject 306 wishes to match when taking a photo from user pose set 302. User pose set 302 may include previous poses of subject 306 from previous photos of subject 306, professional poses (e.g., poses of the subject from photos taken by one or more professional photographers, poses of the subject in professional photos, poses of a specific subject (such as subject 306) from professional photos, poses from pose templates, etc.), a set of stick figures in specific poses (e.g., stick figures depicting specific poses), and / or any other set of user poses.

[0084] exist Figure 3In the illustrative example shown, subject 306 has selected a pose 320 from user pose collection 302. In some examples, selected pose 320 may include a pose depicted in a photo of subject 306 or another subject obtained and / or selected from a photo library in electronic device 100, a photo library of another device, or a photo sharing and / or storage service (such as, for example, a cloud-based photo sharing and / or storage service). In some cases, electronic device 100 may convert a photo (e.g., from a photo library of electronic device 100, a photo library of another device, a photo from a photo sharing and / or storage service, etc.) into a stick figure (e.g., a pose stick figure) depicting selected pose 320, and store the stick figure as part of the user pose collection.

[0085] In some cases, the photo associated with the selected pose 320 (e.g., a photo depicting the selected pose 320, a photo used to create a stick figure depicting the selected pose 320, a photo used to create a representation of the selected pose 320, etc.) can be a scene-based photo and / or a subject-based photo. For example, the photo associated with the selected pose 320 can be selected based on the scene of the photo (e.g., because the scene of the photo is similar or the same as the scene of the photograph being taken, because of a scene preference, because of one or more characteristics of the scene of the photo and / or the photographed subject, such as the subject's mood or a pattern in the scene, etc.), the subject in the photo associated with the selected pose 320, and / or the subject 306.

[0086] After subject 306 attempts to pose in selected pose 620, electronic device 100 may capture (e.g., in response to user input or automatically upon detecting a trigger such as detecting the face of subject 306 and / or a pose of subject 306) preview image 304 of subject 306 in the particular pose of subject 306. Electronic device 100 may then perform image segmentation to generate preview image 310 depicting subject 306. For example, electronic device 100 may perform image segmentation to determine which portions (e.g., which pixels) of preview image 304 correspond to subject 306.

[0087] The electronic device 100 may use the image segmentation result to generate a preview image 310 depicting the subject 306 having the outline of the pose 320. For example, Figure 3As shown, electronic device 100 may generate a preview image 310 depicting subject 306, the preview image having an outline and a bounding box 312 generated based on image segmentation. In some cases, the outline may include an outline of gesture 320. In some cases, the outline may include an outline of subject 306 in preview image 310. In other cases, preview image 310 may include an outline of subject 306 and an outline of gesture 320. In some examples, the outline of gesture 320 may be aligned with the outline of subject 306 to depict any overlap or misalignment between the outline of gesture 320 and the outline of subject 306.

[0088] In some examples, electronic device 100 may compare a portion (e.g., pixels) of preview image 310 corresponding to subject 306 (e.g., as determined based on the image segmentation result) with pose 320 selected by subject 306. Electronic device 100 may use the comparison to determine a match between the pose of subject 306 in preview image 310 and pose 320. For example, electronic device 100 may compare a portion of preview image 310 depicting subject 306 with pose 320, and determine a match or misalignment between the pose of the segmented subject in preview image 310 and pose 320. In some cases, electronic device 100 may use the comparison to determine a score indicating how well and / or how well the pose of subject 306 matches selected pose 320.

[0089] In some examples, electronic device 100 may use the score and / or the comparison result to provide feedback to subject 306. The feedback may help subject 306 adjust subject 306's posture to better match posture 320. In some cases, preview image 310 may include a matching score associated with posture 320 and / or an indication of the amount of matching between posture 320 and the posture of subject 606 in preview image 310. For example, preview image 310 may display a percentage match between posture 320 and the posture of subject 606 in preview image 310.

[0090] In some cases, preview image 310 may depict one or more recommendations for adjusting the pose of subject 306 to better match pose 320. For example, electronic device 100 may determine any aspects of the pose of subject 306 that do not match (e.g., are misaligned) pose 320, and generate feedback with instructions on how to adjust those aspects of the pose of subject 306 to better match pose 320. To illustrate, electronic device 100 may determine that the position of subject 306 and / or a body part of subject 306 (e.g., a hand, head, leg, etc.) is not aligned with pose 320 and / or the same body part reflected in pose 320, and may generate a recommendation to adjust the position, angle, height, placement, orientation, pose, and / or any other aspect of the subject's pose and / or body part to better match pose 320.

[0091] Figure 4 is a diagram illustrating another example implementation of a posture mode. In this example, electronic device 100 depicts preview image 404 of subject 406 in a particular posture. Electronic device 100 may perform image segmentation and implement a pose estimation algorithm to determine the posture of subject 406. For example, in some cases, electronic device 100 may perform image segmentation to detect a portion of preview image 404 that includes subject 406. Electronic device 100 may implement a machine learning model such as a PoseNet model to determine the posture of subject 406 reflected in the portion of the preview image that includes subject 406. In this example, electronic device 100 depicts representation 412 of subject 406 in the detected posture.

[0092] Representation 412 of subject 406 may include a stick figure in the detected pose, a segmentation mask of subject 406 in the detected pose, a segmented portion of preview image 404 depicting subject 406 in the detected pose, or any other representation of subject 406 in the detected pose. Figure 4 In the illustrative example of , representation 412 is a stick figure in a detected pose.

[0093] Subject 406 may select a pose from user pose set 402 that subject 406 wishes to match when taking a photo. Figure 4As shown, subject 406 has selected pose 420 from user pose set 402. Electronic device 100 may compare representation 412 of subject 406 in preview image 410 with pose 420 selected by subject 406. Electronic device 100 may use the comparison to determine a score indicating how well and / or how well the pose of subject 406 matches selected pose 420. For example, electronic device 100 may compare representation 412 of subject 406 with pose 420 and determine a match or misalignment between the pose reflected by representation 412 in preview image 410 and pose 420.

[0094] In some examples, electronic device 100 may use the score and / or the comparison result to provide feedback to subject 406 to help subject 406 better match gesture 420. In some cases, preview image 410 may include a match score associated with gesture 420 and / or an indication of the amount of match between gesture 420 and the gesture reflected by representation 412 of subject 406. For example, preview image 410 may display a percentage match between gesture 420 and the gesture reflected by representation 412 of subject 406.

[0095] In some examples, preview image 410 may depict one or more recommendations for adjusting the pose of subject 406 to better match pose 420. For example, electronic device 100 may determine any aspects of the pose of subject 406 that do not match (e.g., are misaligned) pose 420 and generate feedback with instructions on how to adjust those aspects of the pose of subject 406 to better match pose 420. To illustrate, electronic device 100 may determine that the position of subject 406 or a body part of subject 406 (e.g., a hand, head, leg, etc.) is not aligned with pose 420 and / or the body part as reflected in pose 420. Electronic device 100 may then generate a recommendation to adjust the position, angle, height, placement, orientation, gesture, and / or any other aspect of the pose and / or body part of the subject to better match pose 420.

[0096] Figure 5 is a flow chart illustrating an example process 500 for implementing a gesture mode. At block 502, process 500 may include generating a preview photo of a subject to be photographed. The preview photo may depict the subject in a particular pose, and the electronic device 100 may use the preview photo to generate feedback to adjust the subject's photo pose to better match a selected pose from a set of user poses stored by the electronic device 100.

[0097] At block 504, process 500 may include performing image segmentation to determine which portions of the preview photo correspond to the subject. For example, process 500 may implement an algorithm / model (such as a machine learning model) to perform human image segmentation to identify which pixels of the preview photo correspond to the subject.

[0098] At block 506, process 500 may include determining at least a partial match between one or more gestures from a stored set of user gestures (e.g., stored on electronic device 100) and a detected gesture of a subject in the preview photo. In some cases, determining at least a partial match between one or more gestures from the stored set of user gestures and a detected gesture of a subject in the preview photo may include detecting a gesture of the subject. In some examples, electronic device 100 may determine the gesture of the subject using a machine learning algorithm, such as a self-learning machine learning algorithm.

[0099] In some cases, determining at least a partial match between one or more gestures from a stored user gesture set and a detected gesture of a subject in a preview photo may include comparing the detected gesture of the subject in the preview photo with a stored user gesture set. In some examples, the electronic device 100 may compare the detected gesture of the subject in the preview photo with a stored user gesture set and determine a score for each gesture in the stored user gesture set. The score of a gesture from a stored user gesture set may indicate the extent to which the detected gesture of the subject matches the gesture from the stored user gesture set. For example, the score of a gesture from a stored user gesture set may indicate the amount of overlap, alignment, and / or match between the detected gesture of the subject and the gesture from the stored user gesture set. In some examples, the score may include a percentage value or ratio reflecting the percentage overlap or match ratio between the detected gesture of the subject and the gesture from the stored user gesture set. In other examples, the score may include any other type of value, such as a numerical value, a text value (e.g., high, medium, low), etc.

[0100] In some cases, one or more gestures from the stored set of user gestures may include the top n gestures from the stored set of user gestures. For example, one or more gestures may include gestures from the stored set of user gestures that have top n scores (e.g., top n number of matches) determined based on a comparison between the subject's detected gesture and the stored set of user gestures. In some cases, electronic device 100 may present the one or more gestures via a display of electronic device 100 and / or transmit the one or more gestures to one or more devices associated with the subject.

[0101] At block 508, process 500 may include determining whether the subject has selected any of the one or more poses. For example, as previously mentioned, electronic device 100 may present the one or more poses via a display of electronic device 100 and / or transmit the one or more poses to one or more devices associated with the subject. The subject may view the one or more poses and select a particular pose from the one or more poses. The selected pose may be a pose that the subject would like to have when taking a photo using electronic device 100.

[0102] If the subject does select a pose at block 508, process 500 may proceed to block 512. On the other hand, if the subject does not select a pose from the one or more poses, process 500 may include selecting a pose from the one or more poses based on a match score determined for the one or more poses (e.g., a score determined for the one or more poses based on a determined amount of match / overlap between each of the one or more poses and the subject's detected pose) at block 510. For example, in some cases, if the subject does not select a pose at block 508, electronic device 100 may select the highest matching pose from the one or more poses. After selecting a pose at block 510, process 500 may proceed to block 512.

[0103] At box 512, process 500 may include providing a preview of the subject in the selected posture. For example, electronic device 100 may display the subject in the selected posture and / or transmit the preview image of the subject in the selected posture to one or more devices associated with the subject. In some cases, the preview of the subject in the selected posture may include one or more suggested posture corrections (e.g., determined by electronic device 100) from electronic device 100. For example, the preview of the subject in the selected posture may display a mark identifying one or more body parts of the subject and one or more suggested posture corrections associated with one or more body parts. The mark may include, for example, but not limited to, a pop-up message on one or more body parts of the subject, instructions on how to adjust the position of the subject and / or one or more body parts, one or more arrows and / or any other marks depicting the suggestion of moving or repositioning the subject and / or one or more body parts to better match the selected posture.

[0104] At block 514, process 500 may optionally include determining whether a posture match score (e.g., a score calculated for a selected posture based on a match or amount of match between the selected posture and a detected posture of the subject) for the selected posture is above a threshold. If the posture match score for the selected posture is above the threshold, process 500 may proceed to block 518. On the other hand, if the posture match score for the selected posture is not above the threshold, at block 516, process 500 may include suggesting a posture correction and providing a preview of the subject in the correction posture to the subject. For example, electronic device 100 may display the suggested posture correction and / or transmit the suggested posture correction to one or more devices associated with the subject. Electronic device 100 may capture a preview image of the subject in the correction posture and provide a preview image of the subject in the correction posture to the subject.

[0105] At block 518, process 500 may include capturing a photograph of the subject in the selected pose (or in the corrected pose if correction was performed at block 516). In some examples, capturing a photograph of the subject in the selected pose (or in the corrected pose if correction was performed at block 516) may include enabling or allowing the user to capture a photograph of the subject in the selected pose (or in the corrected pose if correction was performed at block 516).

[0106] Figure 6 is a diagram illustrating an example of automatic gesture correction performed as part of a gesture mode of electronic device 100 (or a camera device of electronic device 100). In some examples, when electronic device 100 detects a face of a subject in a preview image, the electronic device may automatically enable gesture mode. For example, when electronic device 100 generates a preview image of a subject, electronic device 100 may perform face detection on the preview image and automatically enable gesture mode when a face is detected in the preview image. In other examples, a user of electronic device 100 may manually enable gesture mode from a camera application or device settings.

[0107] When electronic device 100 is in gesture mode, a user of electronic device 100 may select a photo pose from user pose collection 602. User pose collection 602 may include previous poses of subject 606 from previous photos of subject 606, professional poses (e.g., poses of a subject from photos taken by one or more professional photographers, poses of a subject in professional photos, poses of a particular subject (such as subject 606) from professional photos, poses from pose templates, etc.), a collection of stick figures in particular poses (e.g., stick figures depicting particular poses), and / or any other user pose collection.

[0108] exist Figure 66, subject 606 has selected pose 620. After subject 606 attempts to strike a pose in selected pose 620, electronic device 100 may capture (e.g., in response to user input or automatically upon detecting a trigger such as detecting the face of subject 606 and / or a pose of subject 606) preview image 604 of subject 606 in a particular pose of subject 606. In some examples, electronic device 100 may perform image segmentation to determine which portions of preview image 604 correspond to subject 606. For example, electronic device 100 may perform image segmentation to determine which pixels of preview image 604 correspond to subject 606. Electronic device 100 may compare the portion of preview image 604 corresponding to subject 606 with pose 620 to determine any misalignment between pose 620 and the pose of subject 606 in preview image 604. In some examples, electronic device 100 may compare a portion of preview image 604 corresponding to subject 606 with gesture 620 to determine an overlap between gesture 620 and the gesture of subject 606 in preview image 604 , and / or a misalignment between gesture 620 and the gesture of subject 606 in preview image 604 .

[0109] Based on any misalignment between pose 620 and the pose of subject 606 in preview image 604, electronic device 100 may perform automatic pose correction to bring the pose of subject 606 within (or substantially within) outline 612 of pose 620. In some examples, electronic device 100 may perform image processing to adjust the pose of subject 606 in the image to bring the pose of subject 606 within (or substantially within) outline 612 of pose 620.

[0110] In some cases, electronic device 100 may generate image 610 depicting subject 606 in a particular pose and outline 612 of pose 620. Outline 612 may be aligned with and / or overlaid on subject 606 in image 610 to depict any misalignment between the pose of subject 606 in image 610 and pose 620. In some cases, electronic device 100 may determine any misalignment between outline 612 of pose 620 and the outline of the pose of subject 606 in image 610, and perform image processing to adjust the pose of subject 606 in image 610 according to outline 612 of pose 620.

[0111] For example, electronic device 100 may correct any misalignment between outline 612 of pose 620 and the outline of the pose of subject 606 in image 610 so that the pose of subject 606 in image 610 is within (or substantially within) outline 612 of pose 620. In some cases, once electronic device 100 performs automatic pose correction, electronic device 100 may output an image of subject 606 in the corrected / adjusted pose and / or store an image of subject 606 in the corrected / adjusted pose.

[0112] In some cases, once electronic device 100 performs automatic posture correction, electronic device 100 may request the user of electronic device 100 (e.g., subject 606 or the user who took the photo of subject 606) to accept or reject the image of subject 606 in the correction / adjustment posture. If the user accepts the image of subject 606 in the correction / adjustment posture, electronic device 100 may output and / or store the image as previously explained. If the user rejects the image of subject 606 in the correction / adjustment posture, electronic device 100 may also adjust the posture of subject 606 in the image so that subject 606 can retake the photo, and / or request input from the user (e.g., subject 606 and / or the user who took the photo from electronic device 100), such as, for example, input requesting a specific posture adjustment, input requesting one or more imaging effects, and input requesting a specific processing of the image, and / or any other input.

[0113] Figure 7 is a flow chart illustrating an example process 700 for performing automatic pose correction as part of a pose mode of electronic device 100 (or a camera device of electronic device 100). In some examples, a subject may select a particular pose from a stored set of user poses (e.g., stored on an electronic device such as electronic device 100), as previously explained. The selected pose may be a pose that the subject wishes to strike for a photograph.

[0114] At block 702, process 700 may include generating a preview photo of a subject to be photographed. The preview photo may depict a pose of the subject, which electronic device 100 may automatically correct to better align with a selected pose.

[0115] At block 704, process 700 may include performing image segmentation to determine which portions of the preview photo correspond to the subject. For example, process 700 may implement an algorithm / model (such as a machine learning model) to perform human image segmentation to identify which pixels of the preview photo correspond to the subject.

[0116] At block 706, process 700 may include determining at least a partial match between one or more gestures from the stored set of user gestures and a detected gesture of a subject in the preview photo. In some cases, determining at least a partial match between one or more gestures from the stored set of user gestures and a detected gesture of a subject in the preview photo may include determining the gesture of the subject. In some examples, electronic device 100 may use a machine learning algorithm to determine the gesture of the subject.

[0117] In some cases, determining at least a partial match between one or more gestures from a stored set of user gestures and a detected gesture of a subject in a preview photo may include comparing the detected gesture of the subject in the preview photo to the stored set of user gestures. In some examples, the electronic device may compare the detected gesture of the subject in the preview photo to the stored set of user gestures and determine a score for each gesture in the stored set of user gestures. The score of a gesture from the stored set of user gestures may indicate the degree to which the detected gesture of the subject matches a gesture from the stored set of user gestures.

[0118] For example, the score of a gesture from a stored set of user gestures may indicate the amount of overlap, match, and / or alignment between the subject's detected gesture and the gesture from the stored set of user gestures. In some cases, the score may include a percentage value or ratio reflecting the percentage overlap or match ratio between the subject's detected gesture and the gesture from the stored set of user gestures. In other cases, the score may include any other type of value, such as a numerical value, a text value (e.g., high, medium, low), etc.

[0119] In some examples, one or more gestures from the stored set of user gestures may include the top n gestures from the stored set of user gestures. For example, one or more gestures may include gestures from the stored set of user gestures that have top n scores (e.g., top n number of matches) determined based on a comparison between the subject's detected gesture and the stored set of user gestures. In some cases, electronic device 100 may present the one or more gestures via a display of electronic device 100 and / or transmit the one or more gestures to one or more devices associated with the subject.

[0120] At block 708, process 700 may include determining whether the subject has selected any of the one or more poses. For example, as previously mentioned, electronic device 100 may present one or more poses via a display of electronic device 100 and / or transmit one or more poses to one or more devices associated with the subject. The subject may view one or more poses and select a particular pose from the one or more poses. The selected pose may be a pose that the subject would like to have when being photographed by electronic device 100.

[0121] If the subject does select a pose at block 708, process 700 may proceed to block 712. On the other hand, if the subject does not select a pose from the one or more poses, process 700 may include selecting a pose from the one or more poses based on a match score determined for the one or more poses (e.g., a score determined for the one or more poses based on a determined amount of match or overlap between each of the one or more poses and the subject's detected pose) at block 710. For example, in some cases, if the subject does not select a pose at block 708, electronic device 100 may select the highest matching pose from the one or more poses. After selecting a pose at block 710, process 700 may proceed to block 712.

[0122] At block 712, process 700 may include automatically adjusting the pose of the subject in the preview photo to better align and / or match the selected pose. In some examples, electronic device 100 may use a machine learning algorithm to automatically adjust the pose. For example, in some cases, electronic device 100 may use a machine learning algorithm to adjust the pose of the subject in the preview photo so that the outline of the subject's pose is within (or substantially within) the outline of the selected pose.

[0123] In some examples, electronic device 100 may perform any automatic pose adjustments by deforming one or more portions of the preview photo to align with (or better align with) the selected pose. For example, electronic device 100 may deform a body shape in the photo corresponding to a subject in the preview photo to align with (or better align with) one or more body shapes in the selected pose. In some cases, electronic device 100 may perform any automatic pose adjustments by performing a pixel coordinate transformation on the preview photo so that the pose of the subject in the preview photo better matches the selected pose.

[0124] At block 714, process 700 may optionally include determining whether a posture match score for the selected posture is above a threshold. The posture match score may include a score calculated for the selected posture based on the amount of overlap or match between the selected posture and the subject's automatically adjusted posture. If the posture match score for the selected posture is above the threshold, process 700 may proceed to block 716. On the other hand, if the posture match score for the selected posture is not above the threshold, process 700 may return to block 712, where electronic device 100 readjusts the subject's posture to better align and / or match the selected posture.

[0125] At block 716, process 700 may include outputting a photograph of the subject in the automatically adjusted pose. In some examples, electronic device 100 may store and / or transmit the photograph of the subject to one or more devices, such as one or more devices of the subject.

[0126] Fig. 8A 800 is a flowchart illustrating an example process 800 for determining a subject's photographic pose. At block 802, process 800 may include enabling a pose mode on a camera device (e.g., camera 102, camera 104) of electronic device 100. In some examples, when electronic device 100 detects a subject's face in a preview image, the electronic device may automatically enable a pose mode on the camera device. For example, when electronic device 100 generates a preview image of a subject, electronic device 100 may perform face detection on the preview image and automatically enable a pose mode when a face is detected in the preview image. In other examples, a user of electronic device 100 may manually enable a pose mode from a camera application, device controls, or device settings.

[0127] At block 804, process 800 may include comparing the subject's detected posture to a stored set of user postures. For example, the subject may pose for a photo, and electronic device 100 may capture a preview image of the subject posing for the photo. Electronic device 100 may then detect the subject's posture from the preview image of the subject and compare the subject's detected posture to the stored set of user postures. In some cases, comparing the subject's detected posture to the stored set of user postures may also include determining a match score for each user posture in the stored set of user postures based on the comparison, as previously described.

[0128] In some cases, if the photo is a group photo with multiple subjects, process 800 may include detecting poses of the subjects in the preview image and comparing the poses to a stored set of user poses at block 804. In some examples, process 800 may include determining a corresponding score for the stored set of user poses based on the comparison between the detected poses and the stored set of user poses.

[0129] At block 806, process 800 may include determining one or more gestures from the stored set of user gestures based on the comparison. For example, electronic device 100 may determine one or more gestures from the stored set of user gestures that best match (e.g., overlap and / or align) the detected subject's gesture. In some cases, electronic device 100 may determine one or more gestures based on corresponding match scores determined for the stored set of user gestures. For example, electronic device 100 may determine gestures with top n match scores. The one or more gestures may include gestures with top n match scores or gestures with the highest match score.

[0130] In some cases, if the photograph is a group photograph with multiple subjects, process 800 at block 806 may include determining a single pose for all subjects in the group photograph or determining multiple poses for multiple subjects in the group photograph.

[0131] At block 808, process 800 may include selecting a pose from one or more poses. For example, electronic device 100 may provide one or more poses to the subject (e.g., by displaying a preview of one or more poses or an indication of one or more poses, and / or by transmitting a preview of one or more poses or an indication of one or more poses to another device associated with one or more subjects). The subject may view the one or more poses provided by electronic device 100 and select from the one or more poses a pose that the subject wishes to have when being photographed. Electronic device 100 may receive an input selection from the subject and proceed to block 810.

[0132] In some cases, if the subject does not want to select any pose from one or more poses, the subject may provide input to the electronic device 100 requesting additional poses, requesting to view a stored set of user poses to expand the pool of poses from which the subject can select a pose, selecting a different pose from the stored set of user poses that is not included in one or more poses, or requesting that the electronic device 100 return to boxes 804 and 806 to determine additional poses, as previously explained.

[0133] As exemplified above, a pose may be manually selected by the subject based on user input. However, in some cases, a pose may be automatically selected by the electronic device 100 based on one or more factors, such as, for example but not limited to: a match score for one or more poses, an understood preference of the subject, the overall scene, a detected mood or emotion of the subject, the type of photograph being taken, the number of subjects in the photograph being taken, and / or any other factor.

[0134] In some cases, if the photograph is a group photograph with multiple subjects, process 800 at block 808 may include selecting a single pose for all subjects in the group photograph or selecting multiple poses for multiple subjects in the group photograph.

[0135] At block 810, process 800 may include capturing a photo of the subject in the selected pose. In some cases, capturing a photo of the subject may include enabling the photo to be captured by a user of electronic device 100 or enabling the user of electronic device 100 to set a timer to allow electronic device 100 to automatically capture the photo.

[0136] In some cases, before capturing a photo of the subject, the electronic device 100 may provide feedback to the subject to help the subject adjust the subject's posture to better match the selected posture. Then, after the subject makes any adjustments to the particular posture based on the feedback provided by the electronic device 100, the electronic device 100 may capture a photo of the subject. In some cases, the electronic device 100 may capture a photo of the subject and then make any automatic posture adjustments. For example, the electronic device 100 may capture a photo of the subject and automatically make any posture adjustments to the photo to make the subject's posture in the photo better match the selected posture.

[0137] In some cases, the electronic device 100 may perform any automatic posture adjustments by performing a geometric transformation of one or more portions (e.g., regions and / or pixels) of the photo corresponding to the subject. In some examples, the electronic device 100 may perform any automatic posture adjustments by deforming one or more portions of the photo corresponding to the subject to align (or better align) with the selected posture. For example, the electronic device 100 may deform the body shape corresponding to the subject in the photo to align (or better align) with one or more body shapes of the selected posture. In some cases, the electronic device 100 may perform any automatic posture adjustments by performing a pixel coordinate transformation on the photo so that the posture of the subject in the photo better matches the selected posture.

[0138] In some examples, electronic device 100 may capture a photograph of the subject after the subject makes any adjustments to a particular pose based on feedback provided by electronic device 100, and automatically make any additional pose adjustments to the photograph to better match the subject's pose in the photograph.

[0139] Figure 8B 8 is a flowchart illustrating another example process 820 for determining a subject's photographic pose. At block 822, process 820 may include enabling a pose mode on a camera device (e.g., camera 102, camera 104) of electronic device 100, as previously described with respect to Fig. 8A As explained in the process 800 shown in FIG.

[0140] At block 824, process 820 may include selecting a pose from a stored set of user poses. In some cases, if the photo is a group photo with multiple subjects, process 820 at block 824 may include selecting a single pose for all subjects in the group photo or selecting multiple poses for multiple subjects in the group photo.

[0141] In some examples, selecting a gesture from a stored set of user gestures may include receiving user input selecting a particular gesture from the stored set of user gestures. For example, electronic device 100 may provide the stored set of user gestures to the subject to allow the subject to select a gesture from the stored set of user gestures. The subject may view the stored set of user gestures provided by electronic device 100 and select a gesture from the stored set of user gestures. Electronic device 100 may receive an input selection from the subject and proceed to block 824.

[0142] In some examples, electronic device 100 may provide the stored set of user gestures to the subject by displaying the stored set of user gestures or displaying an indication of the stored set of user gestures (e.g., a description of each gesture, an outline of each gesture, a representation of each gesture, a preview of the gestures, etc.). In other examples, electronic device 100 may additionally or alternatively provide the stored set of user gestures by transmitting the stored set of user gestures or an indication of the stored set of user gestures to another device associated with one or more subjects.

[0143] At block 826, process 820 may include capturing a preview image of the subject in a particular pose. In some examples, the subject may pose for the preview image in the particular pose, and electronic device 100 may capture the preview image with the subject in the particular pose. In some examples, when posing for the preview image, the subject may attempt to mirror the selected pose. Thus, in some cases, the particular pose may be a pose of the subject attempting to mirror the selected pose.

[0144] At box 828, process 820 may include determining a match between a subject's specific posture in the preview image and a selected posture. For example, in some cases, electronic device 100 may detect a subject's specific posture in the preview image and compare the subject's detected posture with the selected posture. Then, electronic device 100 may determine an amount or score of a match between the subject's specific posture and the selected posture. In some cases, electronic device 100 may compare the subject's specific posture with the selected posture and determine a match score between the subject's specific posture and the selected posture based on the comparison. In some examples, electronic device 100 may determine a score based on an amount or percentage of overlap, alignment, similarity, and / or correspondence between the subject's specific posture and the selected posture.

[0145] In some cases, if the photo is a group photo with multiple subjects, process 820 may include determining a match between the selected pose and one or more poses of one or more of the multiple subjects at block 828. For example, in some cases, electronic device 100 may determine a match between the selected pose and each of the poses of the multiple subjects in the preview image. In some cases, electronic device 100 may determine a match between the selected set of poses and the poses of the subjects in the group photo.

[0146] At block 830, process 820 may include providing feedback to the subject based on the determined match between the subject's particular posture and the selected posture. For example, electronic device 100 may determine any mismatch or misalignment between the subject's particular posture and the selected posture, and provide feedback to the subject on how to adjust the particular posture to better match the selected posture. In some cases, the feedback may include instructions on how to adjust the particular posture (e.g., instructions on what adjustments to make) to increase the match score between the particular posture and the selected posture.

[0147] In some cases, electronic device 100 may provide feedback to the subject until the subject provides input to electronic device 100 to continue adjusting the gesture, or until the subject accepts the adjustment gesture. In other cases, electronic device 100 may provide feedback to the subject until the subject's adjustment gesture reaches a threshold match (e.g., a threshold score, overlap, alignment, similarity, and / or correspondence) between the adjustment gesture and the selected gesture.

[0148] In some examples, the electronic device 100 may provide feedback to the subject by displaying the feedback on a display of the electronic device 100 and / or transmitting the feedback to another device associated with one or more subjects. In some cases, the electronic device 100 may provide the feedback as a message with instructions, an animation illustrating one or more suggested posture adjustments, etc. In some examples, the electronic device 100 may provide the feedback within the preview image of the subject. For example, the electronic device 100 may add the feedback to the preview image of the subject. The feedback may indicate and / or depict one or more suggested adjustments within the preview image of the subject.

[0149] In some cases, if the photo is a group photo with multiple subjects, process 820 may include providing feedback to one or more subjects in the preview image at block 830. For example, in some cases, electronic device 100 may provide feedback to adjust each of the poses of the multiple subjects in the preview image to better match the selected pose or set of poses.

[0150] At block 832, process 820 may include capturing a photo of the subject in a particular pose. In some cases, capturing a photo of the subject may include enabling the photo to be captured by a user of electronic device 100 or enabling the user of electronic device 100 to set a timer to allow electronic device 100 to automatically capture the photo.

[0151] In some examples, electronic device 100 may capture a photo of the subject after the subject makes any adjustments to the particular pose based on feedback provided by electronic device 100. In some cases, electronic device 100 may capture a photo of the subject and subsequently make any automatic pose adjustments, as previously explained. For example, after the subject makes any adjustments to the particular pose based on feedback provided by electronic device 100, electronic device 100 may capture a photo of the subject and automatically make any additional pose adjustments to the photo to better match the subject's pose in the photo with the selected pose.

[0152] In some cases, the electronic device 100 may perform any automatic posture adjustments by performing a geometric transformation of one or more portions (e.g., regions and / or pixels) of the photo corresponding to the subject. In some examples, the electronic device 100 may perform any automatic posture adjustments by deforming one or more portions of the photo corresponding to the subject to align (or better align) with the selected posture. For example, the electronic device 100 may deform the body shape corresponding to the subject in the photo to align (or better align) with one or more body shapes of the selected posture. In some cases, the electronic device 100 may perform any automatic posture adjustments by performing a pixel coordinate transformation on the photo so that the posture of the subject in the photo better matches the selected posture.

[0153] Fig. 9 9 is a diagram illustrating an example posture adjustment of a photographed subject. As shown in the figure, electronic device 100 can capture preview image 904 of subject 910 in a specific posture, and determine a match between the specific posture of subject 910 and selected posture 902.

[0154] exist Fig. 9 In the embodiment of the present invention, selected pose 902 is a stick figure depicting a photographic pose (e.g., a pose stick figure). In other examples, selected pose 902 may be any other representation of a photographic pose. For example, selected pose 902 may include a pose depicted in a previously taken photograph of subject 910 or any other subject. As another example, selected pose 902 may include a visual representation of a pose depicted in a previously taken photograph of subject 910 or any other subject.

[0155] In some cases, selected gesture 902 may include a gesture depicted in a photo of subject 910 or another subject obtained and / or selected from a photo library in electronic device 100, a photo library of another device, or a photo sharing and / or storage service (such as, for example, a cloud-based photo sharing and / or storage service). In some cases, electronic device 100 may convert the photo (e.g., from a photo library of electronic device 100, a photo library of another device, a photo from a photo sharing and / or storage service, etc.) into a stick figure depicting the selected gesture (e.g., a gesture stick figure), and store the stick figure as part of a stored collection of user gestures.

[0156] The photo associated with the selected pose 902 (e.g., a photo depicting the selected pose 902, a photo used to create a stick figure depicting the selected pose 902, a photo used to create a representation of the selected pose 902, etc.) can be a scene-based photo and / or a subject-based photo. For example, the photo associated with the selected pose 902 can be selected based on the scene of the photo (e.g., because the scene of the photo is similar or the same as the scene of the photograph being taken, because of a scene preference, because of one or more characteristics of the scene of the photo and / or the photographed subject, such as the subject's mood or a pattern in the scene, etc.), the subject in the photo associated with the selected pose 902, and / or the subject 910.

[0157] In some examples, when determining a match between subject 910's specific pose and selected pose 902, electronic device 100 may determine an overlap and / or alignment between an outline of subject 910's specific pose and an outline 908 of selected pose 902. In some cases, preview image 904 may depict subject 910 in a specific pose and an outline 908 of selected pose 902. For example, preview image 904 may depict subject 910 in a specific pose, depicting an overlap and / or alignment between subject 910's specific pose and an outline 908 of selected pose 902.

[0158] After determining a match between subject 910's particular pose and selected pose 902, electronic device 100 may provide subject 910 with feedback recommending any adjustments to subject 910's particular pose that would result in a better match between subject 910's pose and selected pose 902. For example, in some cases, electronic device 100 may provide subject 910 with feedback recommending any adjustments to subject 910's particular pose in preview image 904 that would result in a higher match score between subject 910's pose and selected pose 902. In some cases, electronic device 100 may provide subject 910 with feedback recommending any adjustments to subject 910's particular pose in preview image 904 that would bring subject 910's pose within (or substantially within) outline 908 of selected pose 902. In some cases, electronic device 100 may automatically capture an image of subject 910 when the amount of match between subject 910's particular pose and selected pose 902 exceeds a threshold. For example, electronic device 100 may determine whether the amount of match between subject 910's particular pose and selected pose 902 exceeds a threshold. Based on determining that the amount of matches exceeds a threshold, electronic device 100 may trigger a camera of electronic device 100 to automatically capture an image of the subject.

[0159] Feedback to subject 910 may include one or more text instructions with suggested adjustments to a particular posture of subject 910, one or more arrows depicting suggested adjustments to a particular posture (e.g., one or more arrows identifying one or more parts of a particular posture and a direction for moving and / or adjusting those one or more parts), an animation depicting suggested adjustments to a particular posture of subject 910, and the like.

[0160] In some cases, the electronic device 100 may provide feedback within the preview image 904. For example, Fig. 9 , preview image 904 has been modified by electronic device 100 to generate a new preview image 912 depicting feedback for subject 910. In this example, the feedback depicted in preview image 912 includes arrows 914 and 918 indicating which parts of subject 910 should be moved to better match selected pose 902 and the direction to move the parts of subject 910. Specifically, arrow 914 protrudes from the head of subject 910 to indicate that the head of subject 910 should be moved and depicts the direction to move the head of subject 910. Arrow 918 protrudes from the left hand of subject 910 to indicate that the left hand of subject 910 should be moved and depicts the direction to move the left hand of subject 910.

[0161] The feedback depicted in preview image 912 additionally includes text instructions 916 and 920 describing the suggested adjustments to subject 910. For example, text instruction 916 indicates that subject 910 should move the head to the left, and text instruction 920 indicates that subject 910 should move the left leg to the left. In some cases, text instruction 916 may provide an estimated amount by which a particular body part should be moved.

[0162] For example, text instructions 916 may indicate that the head should be rotated an approximate amount or to an approximate position or angle relative to the body of subject 910. As another example, text instructions 920 may indicate that subject 910 should move the left leg to the left by a number of inches (or any other unit). As yet another example, text instructions 920 may indicate that subject 910 should rotate the left foot relative to the body of subject 910 by a specific amount or angle and / or should point in a specific direction relative to the body of subject 910.

[0163] Fig.10 is a diagram illustrating an example of a specific implementation for verifying or adjusting a gesture pattern of user movement associated with an activity. In this example, the activity includes exercise. However, in other examples, the activity may include any other activity, such as, for example, a sports activity, a physical therapy activity, and / or any other activity.

[0164] As shown, electronic device 100 may capture image 1002 of subject 1004 performing an activity. Image 1002 may include a still image of subject 1004 in a particular posture associated with the activity, or a video frame from a sequence of video frames depicting subject 1004 performing the activity. Electronic device 1000 may use image 1002 to recommend adjustments to subject 1004's posture for performing the activity, or to recommend posture and / or movement changes to improve subject 1004's technique when performing the activity.

[0165] Electronic device 100 may compare the pose of subject 1004 in image 1002 (and / or a set of poses and / or movements associated with an activity) with a pose 1006 from a stored set of user poses associated with the activity. Based on the comparison, electronic device 100 may determine a match between the pose of subject 1004 in image 1002 and pose 1006 from the set of user poses. For example, electronic device 100 may determine an overlap and / or alignment between the pose of subject 1004 in image 1002 and pose 1006. Electronic device 100 may additionally or alternatively determine any misalignment between the pose of subject 1004 in image 1002 and pose 1006 and / or any non-overlapping portions of the pose of subject 1004 in image 1002 and pose 1006. Electronic device 100 may determine any recommended adjustments to the pose of subject 1004 in image 1002 so that the pose of subject 1004 better matches (e.g., better aligns and / or overlaps) pose 1006.

[0166] In some examples, electronic device 100 may determine any recommended adjustments to the pose of subject 1004 in image 1002 based on a match between the pose of subject 1004 in image 1002 and pose 1006. For example, electronic device 100 may determine any recommended adjustments to the pose of subject 1002 in image 1004 based on any overlap between the pose of subject 1004 in image 1002 and pose 1006, any alignment between the pose of subject 1004 in image 1002 and pose 1006, any misalignment between the pose of subject 1004 in image 1002 and pose 1006, and / or any non-overlapping portions between the pose of subject 1004 in image 1002 and pose 1006.

[0167] In some examples, the recommended adjustment may include textual instructions for adjusting the pose of subject 1004 to better match pose 1006. In some cases, the recommended adjustment may include an animation depicting the recommended adjustment, one or more arrows and / or other indicia providing information about the recommended adjustment, a preview of the recommended adjustment, and / or the like.

[0168] In some cases, electronic device 100 may display the recommended adjustments on a display device of electronic device 100. In some cases, electronic device 100 may additionally or alternatively communicate these recommended adjustments to one or more devices associated with one or more users (such as subject 1004, a coach or trainer, a parent, a health care professional, etc.).

[0169] Fig.111 is a flow chart illustrating an example process 1100 for adjusting a pose of a photographed subject. At block 1102, process 1100 may include obtaining an image depicting a subject in a first pose via a camera (e.g., camera 102, camera 104) of an electronic device (e.g., electronic device 100).

[0170] At block 1104 , process 1100 may include determining an amount of match between a first pose of a subject depicted in an image and a second pose from a stored set of user poses.

[0171] In some examples, determining an amount of match between a subject's first posture and a second posture from a stored set of user postures may include comparing the subject's first posture to a second posture from a stored set of user postures. In some cases, determining an amount of match may include determining a match score for the second posture based on the comparison of the first posture to the second posture. In some examples, the amount of match may indicate an amount of alignment between a first outline of the subject's first posture and a second outline of the second posture, an amount of overlap between a first outline of the subject's first posture and a second outline of the second posture, a measure of similarity between a first outline of the subject's first posture and a second outline of the second posture, and / or a percentage match between a first outline of the subject's first posture and a second outline of the second posture.

[0172] At block 1106, process 1100 may include generating a recommendation indicating one or more suggested adjustments to the subject's first posture based on the amount of match. In some examples, the one or more suggested adjustments may include one or more adjustments estimated to increase the amount of match between the subject's first posture and a second posture from the stored set of user postures.

[0173] In some aspects, process 1100 may include: determining a respective amount of matches between a subject's first pose and each pose from a stored set of user poses; selecting a second pose from the stored set of user poses based on the respective amount of matches between the subject's first pose and each pose from the stored set of user poses; and in response to selecting the second pose, generating a recommendation indicating one or more suggested adjustments to the subject's first pose. In some examples, the second pose may be a highest matching pose from the stored set of user poses.

[0174] In some aspects, process 1100 may include: comparing a subject's first pose to each pose from a stored set of user poses; determining a respective amount of matching between the subject's first pose and each pose from the stored set of user poses; and determining a plurality of top matching poses (e.g., top n top matching poses) from the stored set of user poses based on the respective amounts of matching between the subject's first pose and each pose from the stored set of user poses. In some examples, the plurality of top matching poses may include the second pose.

[0175] In some aspects, process 1100 may include: generating an indication of multiple top matching postures; receiving user input selecting a second posture from the multiple top matching postures; and selecting the second posture based on the user input. In some aspects, process 1100 may include presenting the indication of multiple top matching postures at a display of an electronic device, or transmitting the indication of multiple top matching postures to one or more devices associated with the subject. In some cases, the indication of multiple top matching postures may include previews of multiple top matching postures. In some aspects, process 1100 may include generating a recommendation indicating one or more suggested adjustments to the first posture of the subject in response to selecting the second posture based on the user input.

[0176] In some examples, generating a recommendation indicating one or more suggested adjustments to a subject's first posture may include: determining one or more differences between the subject's first posture and the second posture from the set of stored user postures based on a comparison between the subject's first posture and the second posture from the set of stored user postures; and determining the one or more suggested adjustments based on the one or more differences between the subject's first posture and the second posture from the set of stored user postures.

[0177] In some aspects, process 1100 may include: obtaining, via a camera of the electronic device, a second image depicting a subject in a third pose; detecting the third pose of the subject in the second image; and determining that the third pose of the subject includes, at least in part, one or more suggested adjustments. In some aspects, process 1100 may include storing the second image depicting the subject in the third pose in response to determining that the third pose of the subject includes the one or more suggested adjustments. In some aspects, process 1100 may include transmitting, to one or more devices associated with the subject, the second image depicting the subject in the third pose in response to determining that the third pose of the subject includes the one or more suggested adjustments.

[0178] In some aspects, process 1100 may include: determining one or more differences between a third pose of the subject and a second pose from a set of stored user poses based on a comparison between the third pose of the subject and a second pose from a set of stored user poses; determining one or more additional adjustments based on the one or more differences between the third pose of the subject and the second pose from the set of stored user poses; and modifying the second image based on the one or more additional adjustments using a machine learning model.

[0179] In some examples, modifying the second image based on the one or more additional adjustments may include performing a geometric transformation of at least a portion of the third pose in the second image associated with the one or more additional adjustments and / or a transformation of a set of pixel coordinates in the second image. The set of pixel coordinates may correspond to pixels depicting at least the portion of the third pose in the second image associated with the one or more additional adjustments.

[0180] In some aspects, process 1100 may include: determining that the subject is facing a display of the electronic device; and presenting, at the display of the electronic device, a recommendation indicating one or more suggested adjustments to the subject's first posture. In some examples, the recommendation may be presented at the display while the subject is facing the display. In some cases, the electronic device may perform facial detection and / or eye gaze tracking to determine that the subject is facing the display. The electronic device may then present the recommendation at the display while the subject is facing the display. In some examples, the display may be a front display of the electronic device, and the recommendation may be presented on the front display while the subject is attempting to capture a selfie or the camera is in selfie or portrait mode.

[0181] In some aspects, process 1100 may include presenting a recommendation indicating one or more suggested adjustments to a first posture of a subject at a first portion of a foldable display of an electronic device. In some examples, the first portion of the foldable display may include a display portion that is at least partially folded relative to a second portion of the foldable display. In some cases, the electronic device may present the recommendation on a folded portion of the display that faces the subject.

[0182] In some aspects, process 1100 may include generating tactile feedback based on one or more suggested adjustments to the subject's first posture, the tactile feedback including a vibration indicating at least one suggested adjustment from the one or more suggested adjustments. In some examples, the vibration may guide the subject to make a posture adjustment according to the one or more suggested adjustments.

[0183] In some aspects, process 1100 may include transmitting one or more suggested adjustments to a device associated with the subject. In some examples, the device may include a watch, a head mounted display, a mobile phone, and / or glasses.

[0184] In some aspects, process 1100 may include automatically capturing an image of the subject when the amount of match exceeds a threshold. For example, the electronic device may determine whether the amount of match between the second posture and the subject's current posture (e.g., the first posture, the first posture with one or more adjustments, etc.) exceeds a threshold. Based on determining that the amount of match exceeds the threshold, the electronic device may trigger a camera to automatically capture an image of the subject.

[0185] In some examples, process 500, process 700, process 800, process 820, and / or process 1100 may be performed by one or more computing devices or apparatuses. In one illustrative example, process 500, process 700, process 800, process 820, and / or process 1100 may be performed by one or more computing devices or apparatuses. Figure 1 In some examples, process 500, process 700, process 800, process 820, and / or process 1100 may be performed by a user having Fig.12 1200. In some cases, such computing devices or apparatuses may include processors, microprocessors, microcomputers, or other components of devices configured to perform the steps of process 500, process 700, process 800, process 820, and / or process 1100. In some examples, such computing devices or apparatuses may include one or more sensors configured to capture image data and / or other sensor measurements. For example, a computing device may include a smart phone, a head-mounted display, a mobile device, or other suitable device. In some examples, such computing devices or apparatuses may include a camera configured to capture one or more images or videos. In some cases, such computing devices may include a display for displaying images. In some examples, one or more sensors and / or cameras are separated from the computing device, in which case the computing device receives the sensed data. Such a computing device may further include a network interface configured to transmit data.

[0186] The components of the computing device may be implemented in circuits. For example, the components may include electronic circuits or other electronic hardware, and / or may be implemented using electronic circuits or other electronic hardware, which may include one or more programmable electronic circuits (e.g., microprocessors, graphics processing units (GPUs), digital signal processors (DSPs), central processing units (CPUs), and / or other suitable electronic circuits), and / or may include computer software, firmware, or any combination thereof for performing the various operations described herein and / or may be implemented using computer software, firmware, or any combination thereof for performing the various operations described herein. The computing device may also include a display (as an example of an output device or as a supplement to an output device), a network interface configured to transmit and / or receive data, any combination thereof, and / or other components. The network interface may be configured to transmit and / or receive data based on an Internet Protocol (IP) or other types of data.

[0187] Process 500, process 700, process 800, process 820, and process 1100 are illustrated as logic flow diagrams, the operations of which represent sequences of operations that can be implemented in hardware, computer instructions, or a combination thereof. In the context of computer instructions, each operation represents a computer-executable instruction stored on one or more computer-readable storage media that, when executed by one or more processors, performs the described operations. Generally speaking, computer-executable instructions include routines, programs, objects, components, data structures, etc. that perform specific functions or implement specific data types. The order in which the operations are described is not intended to be construed as limiting, and any number of the described operations may be combined in any order and / or in parallel to implement a process.

[0188] Additionally, process 500, process 700, process 800, process 820, and / or process 1100 may be executed under the control of one or more computer systems configured with executable instructions, and may be implemented by hardware as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed together on one or more processors, or a combination thereof. As described above, the code may be stored on a computer-readable or machine-readable storage medium, for example, in the form of a computer program including multiple instructions that can be executed by one or more processors. The computer-readable or machine-readable storage medium may be non-transitory.

[0189] Fig.12 An example computing device architecture 1200 is illustrated that illustrates an example computing device that can implement the various techniques described herein. For example, the computing device architecture 1200 can implement Figure 11200. The components of the computing device architecture 1200 are shown in electrical communication with each other using a connection 1205, such as a bus. The example computing device architecture 1200 includes a processing unit (CPU or processor) 1210 and a computing device connection 1205 that couples various computing device components including computing device memory 1215, such as read-only memory (ROM) 1220 and random access memory (RAM) 1225, to the processor 1210.

[0190] The computing device architecture 1200 may include a cache of high-speed memory directly connected to the processor 1210, near the processor, or integrated as part of the processor. The computing device architecture 1200 may copy data from the memory 1215 and / or the storage device 1230 to the cache 1212 for fast access by the processor 1210. In this way, the cache can provide a performance improvement that avoids the processor 1210 from delaying while waiting for data. These and other modules can control or be configured to control the processor 1210 to perform various actions. Other computing device memories 1215 can also be used. The memory 1215 may include a variety of different types of memory with different performance characteristics. The processor 1210 may include any general-purpose processor and hardware or software services stored in the storage device 1230 and configured to control the processor 1210, as well as a special-purpose processor in which software instructions are incorporated into the processor design. The processor 1210 may be a self-contained system including multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.

[0191] To enable user interaction with the computing device architecture 1200, the input device 1245 may represent any number of input mechanisms, such as a microphone for voice, a touch-sensitive screen for gesture or graphic input, a keyboard, a mouse, motion input, voice, etc. The output device 1235 may also be one or more of a plurality of output mechanisms known to those skilled in the art, such as a display, a projector, a television, a speaker device. In some instances, a multimodal computing device may enable a user to provide multiple types of input to communicate with the computing device architecture 1200. The communication interface 1240 may generally control and manage user input and computing device output. There is no restriction on operating on any particular hardware arrangement, and thus the underlying features herein may be easily replaced to obtain improved hardware or firmware arrangements as they are developed.

[0192] The storage device 1230 is a non-volatile memory and may be a hard disk or other type of computer readable medium capable of storing computer-accessible data, such as a magnetic tape cartridge, a flash memory card, a solid-state memory device, a digital versatile disk, a cassette tape, a random access memory (RAM) 1225, a read-only memory (ROM) 1220, and hybrids thereof. The storage device 1230 may include software, code, firmware, etc. for controlling the processor 1210. Other hardware or software modules are contemplated. The storage device 1230 may be connected to the computing device connector 1205. In one aspect, a hardware module that performs a particular function may include a software component stored in a computer readable medium that is combined with necessary hardware components such as the processor 1210, the connector 1205, the output device 1235, etc. to implement the function.

[0193] The term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing or carrying instructions and / or data. Computer-readable media may include non-transient media in which data may be stored and does not include carrier waves and / or transient electronic signals propagated wirelessly or on a wired connection. Examples of non-transient media may include, but are not limited to, disks or tapes, optical storage media (such as compact discs (CDs) or digital versatile discs (DVDs)), flash memory, memory, or memory devices. Computer-readable media may store thereon code and / or machine-executable instructions, which may represent procedures, functions, subroutines, programs, routines, subroutines, modules, software packages, categories, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, independent variables, parameters, or memory contents. Information, independent variables, parameters, data, etc. may be passed, forwarded, or sent via any suitable means, including memory sharing, message passing, token passing, network sending, etc.

[0194] In some embodiments, computer-readable storage devices, media, and memories may include wired or wireless signals including bit streams, etc. However, when referred to, non-transitory computer-readable storage media specifically excludes media such as power consumption, carrier signals, electromagnetic waves, and signals themselves.

[0195] Specific details are provided in the above description to provide a thorough understanding of the embodiments and examples provided herein. However, it will be appreciated by those skilled in the art that embodiments can be put into practice without these specific details. For clarity of explanation, in some instances, the present technology may be presented as including a separate functional block, which includes a device, device assembly, step or routine in a method embodied in a combination of software or hardware and software. Additional components other than those components shown in the accompanying drawings and / or described herein may be used. For example, circuits, systems, networks, processes and other components may be shown as components in block diagram form to avoid obscuring these embodiments in unnecessary details. In other instances, known circuits, processes, algorithms, structures and techniques may be shown without necessary details to avoid confusing each embodiment.

[0196] Individual embodiments may be described above as processes or methods depicted as flow charts, flow diagrams, data flow diagrams, structure diagrams, or block diagrams. Although flow charts may describe operations as sequential processes, many operations in the operations may be performed in parallel or concurrently. In addition, the order of the operations may be rearranged. The process is terminated when the operations of the process are completed, but the process may have additional steps not included in the accompanying drawings. The process may correspond to a method, function, procedure, subroutine, subprogram, etc. When a process corresponds to a function, the termination of the process may correspond to the function returning to the calling function or main function.

[0197] The processes and methods according to the above examples can be implemented using stored computer executable instructions or otherwise obtained from computer readable media. Such instructions may include, for example, instructions and data that cause or otherwise configure a general-purpose computer, a special-purpose computer, or a processing device to perform a certain function or functional group. Parts of the computer resources used can be accessed through a network. Computer executable instructions can be, for example, binary, intermediate format instructions such as assembly language, firmware, source code. Examples of computer readable media that can be used to store instructions, information used, and / or information created during the method according to the described examples include disks or optical disks, flash memories, USB devices with non-volatile memory, networked storage devices, etc.

[0198] The devices implementing the processes and methods according to these disclosures may include hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof, and may take any of a variety of form factors. When implemented in software, firmware, middleware, or microcode, program code or code segments (e.g., computer program products) for performing necessary tasks may be stored in a computer-readable or machine-readable medium. The processor may perform the necessary tasks. Typical examples of form factors include laptop computers, smart phones, mobile phones, tablet devices, or other small form factor personal computers, personal digital assistants, rack-mounted devices, stand-alone devices, etc. The functionality described herein may also be embodied in peripheral devices or plug-in cards. By way of further example, such functionality may also be implemented on circuit boards among different chips or different processes executed on a single device.

[0199] Instructions, media for communicating such instructions, computing resources for executing them, and other structures for supporting such computing resources are example means for providing the functionality described in this disclosure.

[0200] In the foregoing description, various aspects of the present application are described with reference to the specific embodiments of the present application, but those skilled in the art will recognize that the present application is not limited thereto. Thus, although the exemplary embodiments of the present application have been described in detail herein, it is to be understood that the inventive concept can be embodied and adopted in various other ways, and the appended claims are intended to be interpreted as including these variations, unless limited by the prior art. Various features and aspects of the above-mentioned applications can be used individually or in combination. In addition, without departing from the broader essence and scope of this specification, the embodiments can be used in any number of environments and applications beyond the environments and applications described herein. Therefore, the description and the accompanying drawings should be considered as illustrative rather than restrictive. For the purpose of illustration, each method is described in a specific order. It should be understood that in an alternative embodiment, each method can be performed in a different order than described.

[0201] One of ordinary skill in the art will understand that the less than ("<") and greater than (">") symbols or terms used herein may be replaced by less than or equal to ("≤") and greater than or equal to ("≥") symbols, respectively, without departing from the scope of this specification.

[0202] Where a component is described as being “configured to” perform certain operations, such configuration may be achieved, for example, by designing electronic circuits or other hardware to perform the operations, by programming programmable electronic circuits (e.g., a microprocessor or other suitable electronic circuits) to perform the operations, or any combination thereof.

[0203] The phrase "coupled to" means that any component is directly or indirectly physically connected to another component, and / or any component is directly or indirectly in communication with another component (e.g., connected to another component via a wired or wireless connection and / or other suitable communication interface).

[0204] Claim language or other language in this disclosure that states "at least one of" a set and / or "one or more of" a set indicates that one member of the set or multiple members of the set (in any combination) satisfies the claim. For example, claim language that states "at least one of A and B" or "at least one of A or B" means A, B, or A and B. In another example, claim language that states "at least one of A, B, and C" or "at least one of A, B, or C" means A, B, C, or A and B, or A and C, or B and C, or A and B and C. The language "at least one of" a set and / or "one or more of" a set does not limit the set to the items listed in the set. For example, claim language that states "at least one of A and B" or "at least one of A or B" may mean A, B, or A and B, and may additionally include items not listed in the set of A and B.

[0205] Various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the examples disclosed herein may be implemented as electronic hardware, computer software, firmware, or a combination thereof. In order to clearly illustrate this interchangeability of hardware and software, various illustrative components, frames, modules, circuits, and steps have been generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints proposed for the entire system. The technician may implement the described functionality in different ways for each specific application, but such specific implementation decisions should not be interpreted as departing from the scope of the present application.

[0206] The technology described herein can also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such technology can be implemented in any of a variety of devices, such as general-purpose computers, wireless communication device mobile phones, or integrated circuit devices with multiple uses, including applications in wireless communication device mobile phones and other devices. Any features described as modules or components can be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the technology can be implemented at least in part by a computer-readable data storage medium including a program code, which includes instructions for executing one or more of the above-mentioned methods, algorithms, and / or operations when executed. Computer-readable data storage media can form part of a computer program product, which can include packaging materials. Computer-readable media can include memory or data storage media, such as random access memory (RAM) (such as synchronous dynamic random access memory (SDRAM)), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage media, etc. Additionally or alternatively, the technology may be implemented at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and that can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.

[0207] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such processors may be configured to perform any of the techniques described in this disclosure. A general-purpose processor may be a microprocessor; however, in an alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration. Therefore, the term "processor" as used herein may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or device suitable for implementing the techniques described herein.

[0208] Illustrative examples of the present disclosure include:

[0209] Aspect 1. A device for adjusting the posture of a subject in a photograph, the device comprising: a memory; and one or more processors, the one or more processors coupled to the memory, the one or more processors configured to: obtain an image depicting a subject in a first posture via a camera of the device; determine an amount of match between the first posture of the subject depicted in the image and a second posture from a stored set of user postures; and based on the amount of match, generate a recommendation indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase the amount of match between the first posture of the subject and the second posture from the stored set of user postures.

[0210] Aspect 2. An apparatus according to Aspect 1, wherein in order to determine the amount of match between the first posture of the subject and the second posture from the stored set of user postures, the one or more processors are configured to: compare the first posture of the subject with the second posture from the stored set of user postures.

[0211] Aspect 3. An apparatus according to Aspect 2, wherein the match amount indicates at least one of: an amount of alignment between a first outline of the subject in the first posture and a second outline of the second posture, an amount of overlap between the first outline of the subject in the first posture and the second outline of the second posture, a measure of similarity between the first outline of the subject in the first posture and the second outline of the second posture, and a percentage match between the first outline of the subject in the first posture and the second outline of the second posture.

[0212] Aspect 4. An apparatus according to any one of Aspects 1 to 3, wherein the one or more processors are configured to: determine a corresponding amount of matching between the first posture of the subject and each posture from the stored set of user postures; select the second posture from the stored set of user postures based on the corresponding amount of matching between the first posture of the subject and each posture from the stored set of user postures, wherein the second posture includes the highest matching posture from the stored set of user postures; and in response to selecting the second posture, generate the recommendation indicating the one or more suggested adjustments to the first posture of the subject.

[0213] Aspect 5. An apparatus according to any one of Aspects 1 to 4, wherein the one or more processors are configured to: compare the first posture of the subject with each posture from the stored user posture set; determine a corresponding amount of matching between the first posture of the subject and each posture from the stored user posture set; and determine a plurality of highest matching postures from the stored user posture set based on the corresponding amount of matching between the first posture of the subject and each posture from the stored user posture set, wherein the plurality of highest matching postures include the second posture.

[0214] Aspect 6. An apparatus according to Aspect 5, wherein the one or more processors are configured to: generate an indication of the multiple highest matching postures; receive user input to select the second posture from the multiple highest matching postures; and select the second posture based on the user input.

[0215] Aspect 7. An apparatus according to Aspect 6, wherein the one or more processors are configured to present the indications of the multiple highest matching postures on a display of the apparatus, or to transmit the indications of the multiple highest matching postures to one or more devices associated with the subject.

[0216] Aspect 8. An apparatus according to any one of Aspects 6 to 7, wherein the indication of the plurality of highest matching gestures comprises a preview of the plurality of highest matching gestures.

[0217] Aspect 9. An apparatus according to any one of Aspects 6 to 8, wherein the one or more processors are configured to: in response to selecting the second posture based on the user input, generate the recommendation indicating the one or more suggested adjustments to the first posture of the subject.

[0218] Aspect 10. An apparatus according to any one of Aspects 1 to 9, wherein the one or more processors are configured to: update the stored set of user gestures to include a specific gesture of the subject depicted in one or more images of the subject.

[0219] Aspect 11. An apparatus according to any one of Aspects 1 to 10, wherein the one or more processors are configured to: determine that the subject is facing a display of the apparatus; and present, at the display of the apparatus, the recommendation indicating one or more suggested adjustments to the first posture of the subject, the recommendation being presented at the display when the subject is facing the display.

[0220] Aspect 12. An apparatus according to any one of Aspects 1 to 11, wherein the one or more processors are configured to: present the recommendation indicating one or more suggested adjustments to the first posture of the subject at a first portion of a foldable display of the apparatus, the first portion of the foldable display comprising a display portion that is at least partially folded relative to a second portion of the foldable display.

[0221] Aspect 13. An apparatus according to any one of Aspects 1 to 12, wherein the one or more processors are configured to: generate tactile feedback based on the one or more suggested adjustments to the first posture of the subject, the tactile feedback comprising a vibration indicating at least one suggested adjustment from the one or more suggested adjustments.

[0222] Aspect 14. An apparatus according to any one of Aspects 1 to 13, wherein the one or more processors are configured to: transmit the one or more recommended adjustments to a device associated with the subject, the device comprising at least one of a watch, a head-mounted display, a mobile phone, and glasses.

[0223] Aspect 15. An apparatus according to any one of Aspects 1 to 14, wherein in order to generate the recommendation indicating the one or more suggested adjustments to the first posture of the subject, the one or more processors are configured to: determine one or more differences between the first posture of the subject and the second posture from the stored set of user postures based on a comparison between the first posture of the subject and the second posture from the stored set of user postures; and determine the one or more suggested adjustments based on the one or more differences between the first posture of the subject and the second posture from the stored set of user postures.

[0224] Aspect 16. An apparatus according to any one of Aspects 1 to 15, wherein the one or more processors are configured to: obtain, via the camera of the apparatus, a second image depicting the subject in a third posture; detect the third posture of the subject in the second image; and determine that the third posture of the subject at least partially includes the one or more suggested adjustments.

[0225] Aspect 17. An apparatus according to Aspect 16, wherein the one or more processors are configured to: in response to determining that the third posture of the subject includes the one or more suggested adjustments, store the second image depicting the subject in the third posture.

[0226] Aspect 18. An apparatus according to any one of Aspects 16 to 17, wherein the one or more processors are configured to: in response to determining that the third posture of the subject includes the one or more suggested adjustments, transmit the second image depicting the subject in the third posture to one or more devices associated with the subject.

[0227] Aspect 19. An apparatus according to any one of Aspects 16 to 18, wherein the one or more processors are configured to: determine one or more differences between the third posture of the subject and the second posture from the stored set of user postures based on a comparison between the third posture of the subject and the second posture from the stored set of user postures; determine one or more additional adjustments based on the one or more differences between the third posture of the subject and the second posture from the stored set of user postures; and modify the second image based on the one or more additional adjustments using a machine learning model.

[0228] Aspect 20. An apparatus according to Aspect 19, wherein in order to modify the second image based on the one or more additional adjustments, the one or more processors are configured to: perform at least one of a geometric transformation of at least a portion of the third posture in the second image associated with the one or more additional adjustments and a transformation of a set of pixel coordinates in the second image, the set of pixel coordinates corresponding to pixels depicting at least the portion of the third posture in the second image associated with the one or more additional adjustments.

[0229] Aspect 21. The device according to any one of aspects 1 to 20, further comprising the camera.

[0230] Aspect 22. An apparatus according to any one of aspects 1 to 21, wherein the apparatus comprises a mobile device.

[0231] Aspect 23. A method for adjusting the posture of a subject in a photograph, the method comprising: obtaining an image depicting a subject in a first posture via a camera of an electronic device; determining an amount of match between the first posture of the subject depicted in the image and a second posture from a stored set of user postures; and based on the amount of match, generating a recommendation indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase the amount of match between the first posture of the subject and the second posture from the stored set of user postures.

[0232] Aspect 24. A method according to Aspect 23, wherein determining the amount of match between the first posture of the subject and the second posture from the stored set of user postures includes: comparing the first posture of the subject with the second posture from the stored set of user postures.

[0233] Aspect 25. An apparatus according to Aspect 24, wherein the match amount indicates at least one of: an amount of alignment between a first outline of the subject in the first posture and a second outline of the second posture, an amount of overlap between the first outline of the subject in the first posture and the second outline of the second posture, a measure of similarity between the first outline of the subject in the first posture and the second outline of the second posture, and a percentage match between the first outline of the subject in the first posture and the second outline of the second posture.

[0234] Aspect 26. A method according to any one of Aspects 23 to 25, the method further comprising: determining a corresponding amount of matching between the first posture of the subject and each posture from the stored set of user postures; selecting the second posture from the stored set of user postures based on the corresponding amount of matching between the first posture of the subject and each posture from the stored set of user postures, wherein the second posture includes the highest matching posture from the stored set of user postures; and in response to selecting the second posture, generating the recommendation indicating the one or more suggested adjustments to the first posture of the subject.

[0235] Aspect 27. According to any one of Aspects 23 to 26, the method further includes: comparing the first posture of the subject with each posture from the stored user posture set; determining the corresponding matching amount between the first posture of the subject and each posture from the stored user posture set; and based on the corresponding matching amount between the first posture of the subject and each posture from the stored user posture set, determining a plurality of highest matching postures from the stored user posture set, wherein the plurality of highest matching postures include the second posture.

[0236] Aspect 28. The method according to aspect 27 further includes: generating an indication of the multiple highest matching postures; receiving user input selecting the second posture from the multiple highest matching postures; and selecting the second posture based on the user input.

[0237] Aspect 29. An apparatus according to Aspect 28, further comprising presenting the indication of the multiple highest matching postures on a display of the electronic device, or transmitting the indication of the multiple highest matching postures to one or more devices associated with the subject.

[0238] Aspect 30. An apparatus according to any one of aspects 27 to 29, wherein the indication of the plurality of highest matching gestures comprises a preview of the plurality of highest matching gestures.

[0239] Aspect 31. An apparatus according to any one of Aspects 27 to 30, further comprising: in response to selecting the second posture based on the user input, generating the recommendation indicating the one or more suggested adjustments to the first posture of the subject.

[0240] Aspect 32. The method according to any one of Aspects 23 to 31, further comprising: updating the stored set of user gestures to include a specific gesture of the subject depicted in one or more images of the subject.

[0241] Aspect 33. A method according to any one of Aspects 23 to 32, the method further comprising: determining that the subject is facing a display of the device; and presenting the recommendation indicating one or more suggested adjustments to the first posture of the subject at the display of the electronic device, the recommendation being presented at the display when the subject is facing the display.

[0242] Aspect 34. A method according to any one of Aspects 23 to 33, the method further comprising: presenting the recommendation indicating one or more suggested adjustments to the first posture of the subject at a first portion of a foldable display of the electronic device, the first portion of the foldable display comprising a display portion that is at least partially folded relative to a second portion of the foldable display.

[0243] Aspect 35. A method according to any one of Aspects 23 to 34, the method further comprising: generating tactile feedback based on the one or more suggested adjustments to the first posture of the subject, the tactile feedback comprising a vibration indicating at least one suggested adjustment from the one or more suggested adjustments.

[0244] Aspect 36. The method according to any one of Aspects 23 to 35, further comprising: transmitting the one or more recommended adjustments to a device associated with the subject, the device comprising at least one of a watch, a head-mounted display, a mobile phone, and glasses.

[0245] Aspect 37. A method according to any one of Aspects 23 to 36, wherein generating the recommendation indicating the one or more suggested adjustments to the first posture of the subject comprises: determining one or more differences between the first posture of the subject and the second posture from the stored set of user postures based on a comparison between the first posture of the subject and the second posture from the stored set of user postures; and determining the one or more suggested adjustments based on the one or more differences between the first posture of the subject and the second posture from the stored set of user postures.

[0246] Aspect 38. According to any one of Aspects 23 to 37, the method also includes: obtaining, via the camera of the electronic device, a second image depicting the subject in a third posture; detecting the third posture of the subject in the second image; and determining that the third posture of the subject at least partially includes the one or more suggested adjustments.

[0247] Aspect 39. The method of aspect 38, further comprising: in response to determining that the third posture of the subject includes the one or more suggested adjustments, storing the second image depicting the subject in the third posture.

[0248] Aspect 40. A method according to any one of Aspects 38 to 39, the method further comprising: in response to determining that the third posture of the subject includes the one or more suggested adjustments, transmitting the second image depicting the subject in the third posture to one or more devices associated with the subject.

[0249] Aspect 41. A method according to any one of Aspects 38 to 40, the method further comprising: determining one or more differences between the third posture of the subject and the second posture from the stored user posture set based on a comparison between the third posture of the subject and the second posture from the stored user posture set; determining one or more additional adjustments based on the one or more differences between the third posture of the subject and the second posture from the stored user posture set; and modifying the second image based on the one or more additional adjustments using a machine learning model.

[0250] Aspect 42. A method according to Aspect 41, wherein modifying the second image based on the one or more additional adjustments includes: performing at least one of a geometric transformation of at least a portion of the third posture in the second image associated with the one or more additional adjustments and a transformation of a set of pixel coordinates in the second image, the set of pixel coordinates corresponding to pixels depicting at least the portion of the third posture in the second image associated with the one or more additional adjustments.

[0251] Aspect 43. An apparatus comprising means for performing a method according to any one of aspects 23 to 42.

[0252] Aspect 44. A non-transitory computer-readable medium having instructions stored thereon, which, when executed by one or more processors, cause the one or more processors to perform a method according to any one of Aspects 23 to 42.

Claims

1. A device for adjusting the posture of a subject in a photograph, the device comprising: Memory; and one or more processors, the one or more processors coupled to the memory, the one or more processors configured to: obtaining, via a camera of the device, an image depicting the subject in a first pose; determining an amount of match between the first posture of the subject depicted in the image and a second posture from a stored set of user postures; as well as Based on the amount of match, a recommendation is generated indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase the amount of match between the first posture of the subject and the second posture from the stored set of user postures.

2. The apparatus of claim 1 , wherein to determine the amount of match between the first posture of the subject and the second posture from the stored set of user postures, the one or more processors are configured to: The first posture of the subject is compared to the second posture from the stored set of user postures.

3. A device according to claim 2, wherein the match amount indicates at least one of: an amount of alignment between a first outline of the subject in the first posture and a second outline of the second posture, an amount of overlap between the first outline of the subject in the first posture and the second outline of the second posture, a measure of similarity between the first outline of the subject in the first posture and the second outline of the second posture, and a percentage match between the first outline of the subject in the first posture and the second outline of the second posture.

4. The apparatus of claim 1 , wherein the one or more processors are configured to: determining a respective amount of match between the first posture of the subject and each posture from the stored set of user postures; selecting the second posture from the stored set of user postures based on the respective amounts of matches between the first posture of the subject and each posture from the stored set of user postures, wherein the second posture comprises a highest matching posture from the stored set of user postures; as well as In response to selecting the second posture, the recommendation is generated indicating the one or more suggested adjustments to the first posture of the subject.

5. The apparatus of claim 1 , wherein the one or more processors are configured to: comparing the first posture of the subject to each posture from the stored set of user postures; determining a respective amount of match between the first posture of the subject and each posture from the stored set of user postures; as well as Based on the respective amounts of matches between the subject's first posture and each posture from the stored set of user postures, a plurality of top matching postures from the stored set of user postures are determined, wherein the plurality of top matching postures includes the second posture.

6. The apparatus of claim 5, wherein the one or more processors are configured to: generating an indication of the plurality of highest matching gestures; receiving user input selecting the second gesture from among the plurality of highest matching gestures; and The second gesture is selected based on the user input.

7. An apparatus according to claim 6, wherein the one or more processors are configured to present the indications of the multiple highest matching postures at a display of the apparatus, or to transmit the indications of the multiple highest matching postures to one or more devices associated with the subject. The apparatus of claim 6 , wherein the indication of the plurality of top matching gestures comprises a preview of the plurality of top matching gestures.

9. The apparatus of claim 6, wherein the one or more processors are configured to: In response to selecting the second posture based on the user input, the recommendation is generated indicating the one or more suggested adjustments to the first posture of the subject.

10. The apparatus of claim 1, wherein the one or more processors are configured to: The stored set of user gestures is updated to include a specific gesture of the subject depicted in the one or more images of the subject.

11. The apparatus of claim 1 , wherein the one or more processors are configured to: determining that the subject is facing a display of the device; and The recommendation is presented at the display of the apparatus indicating one or more suggested adjustments to the first posture of the subject, the recommendation being presented at the display when the subject is facing the display.

12. The apparatus of claim 1, wherein the one or more processors are configured to: The recommendation indicating one or more suggested adjustments to the first posture of the subject is presented at a first portion of a foldable display of the device, the first portion of the foldable display comprising a display portion that is at least partially folded relative to a second portion of the foldable display.

13. The apparatus of claim 1, wherein the one or more processors are configured to: Based on the one or more suggested adjustments to the first posture of the subject, haptic feedback is generated, the haptic feedback comprising a vibration indicative of at least one suggested adjustment from the one or more suggested adjustments.

14. The apparatus of claim 1, wherein the one or more processors are configured to: The one or more suggested adjustments are communicated to a device associated with the subject, the device comprising at least one of a watch, a head mounted display, a mobile phone, and glasses.

15. The apparatus of claim 1 , wherein to generate the recommendation indicating the one or more suggested adjustments to the first posture of the subject, the one or more processors are configured to: determining one or more differences between the first posture of the subject and the second posture from the stored set of user postures based on a comparison between the first posture of the subject and the second posture from the stored set of user postures; and The one or more suggested adjustments are determined based on the one or more differences between the first posture of the subject and the second posture from the stored set of user postures.

16. The apparatus of claim 1, wherein the one or more processors are configured to: obtaining, via the camera of the device, a second image depicting the subject in a third pose; detecting the third posture of the subject in the second image; and Determining the third posture of the subject includes, at least in part, the one or more suggested adjustments.

17. The apparatus of claim 16, wherein the one or more processors are configured to: In response to determining that the third pose of the subject includes the one or more suggested adjustments, storing the second image depicting the subject in the third pose.

18. The apparatus of claim 16, wherein the one or more processors are configured to: In response to determining that the third pose of the subject includes the one or more suggested adjustments, transmitting the second image depicting the subject in the third pose to one or more devices associated with the subject.

19. The apparatus of claim 16, wherein the one or more processors are configured to: determining one or more differences between the third posture of the subject and the second posture from the stored set of user postures based on a comparison between the third posture of the subject and the second posture from the stored set of user postures; determining one or more additional adjustments based on the one or more differences between the third posture of the subject and the second posture from the stored set of user postures; as well as The second image is modified based on the one or more additional adjustments using a machine learning model.

20. The apparatus of claim 19, wherein to modify the second image based on the one or more additional adjustments, the one or more processors are configured to: Perform at least one of a geometric transformation of at least a portion of the third posture in the second image associated with the one or more additional adjustments and a transformation of a set of pixel coordinates in the second image corresponding to pixels depicting at least the portion of the third posture in the second image associated with the one or more additional adjustments.

21. The device of claim 1, further comprising the camera.

22. The apparatus of claim 1, wherein the apparatus comprises a mobile device.

23. A method for adjusting the posture of a subject in a photograph, the method comprising: obtaining, via a camera of the electronic device, an image depicting the subject in a first posture; determining an amount of match between the first posture of the subject depicted in the image and a second posture from a stored set of user postures; as well as Based on the amount of match, a recommendation is generated indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase the amount of match between the first posture of the subject and the second posture from the stored set of user postures.

24. The method according to claim 23, further comprising: determining a respective amount of match between the first posture of the subject and each posture from the stored set of user postures; selecting the second posture from the stored set of user postures based on the respective amounts of matches between the first posture of the subject and each posture from the stored set of user postures, wherein the second posture comprises a highest matching posture from the stored set of user postures; as well as In response to selecting the second posture, the recommendation is generated indicating the one or more suggested adjustments to the first posture of the subject.

25. The method according to claim 23, further comprising: comparing the first posture of the subject to each posture from the stored set of user postures; determining a respective amount of match between the first posture of the subject and each posture from the stored set of user postures; as well as Based on the respective amounts of matches between the subject's first posture and each posture from the stored set of user postures, a plurality of top matching postures from the stored set of user postures are determined, wherein the plurality of top matching postures includes the second posture.

26. The method according to claim 25, further comprising: generating an indication of the plurality of highest matching gestures; receiving user input selecting the second gesture from among the plurality of highest matching gestures; as well as The second gesture is selected based on the user input.

27. The method of claim 26, further comprising presenting the indication of the plurality of highest matching postures at a display of the electronic device, or transmitting the indication of the plurality of highest matching postures to one or more devices associated with the subject.

28. The method of claim 26, wherein the indication of the plurality of top matching gestures comprises a preview of the plurality of top matching gestures.

29. The method according to claim 26, further comprising: In response to selecting the second posture based on the user input, the recommendation is generated indicating the one or more suggested adjustments to the first posture of the subject.

30. The method of claim 26, wherein generating the recommendation indicating the one or more suggested adjustments to the first posture of the subject comprises: determining one or more differences between the first posture of the subject and the second posture from the stored set of user postures based on a comparison between the first posture of the subject and the second posture from the stored set of user postures; as well as The one or more suggested adjustments are determined based on the one or more differences between the first posture of the subject and the second posture from the stored set of user postures.

31. The method of claim 23, further comprising: obtaining, via the camera of the electronic device, a second image depicting the subject in a third pose; detecting the third posture of the subject in the second image; determining that the third posture of the subject includes, at least in part, the one or more suggested adjustments; as well as In response to determining that the third pose of the subject includes the one or more suggested adjustments, transmitting the second image depicting the subject in the third pose to one or more devices associated with the subject.

32. The method according to claim 31, further comprising: determining one or more differences between the third posture of the subject and the second posture from the stored set of user postures based on a comparison between the third posture of the subject and the second posture from the stored set of user postures; determining one or more additional adjustments based on the one or more differences between the third posture of the subject and the second posture from the stored set of user postures; as well as The second image is modified based on the one or more additional adjustments using a machine learning model.

33. The method of claim 23, further comprising: The stored set of user gestures is updated to include a specific gesture of the subject depicted in the one or more images of the subject.

34. The method of claim 23, further comprising: determining that the subject is facing a display of the electronic device; as well as The recommendation is presented at the display of the electronic device indicating one or more suggested adjustments to the first posture of the subject, the recommendation being presented at the display when the subject is facing the display.

35. The method of claim 23, further comprising: The recommendation indicating one or more suggested adjustments to the first posture of the subject is presented at a first portion of a foldable display of the electronic device, the first portion of the foldable display comprising a display portion that is at least partially folded relative to a second portion of the foldable display.

36. The method of claim 23, further comprising: Based on the one or more suggested adjustments to the first posture of the subject, haptic feedback is generated, the haptic feedback comprising a vibration indicative of at least one suggested adjustment from the one or more suggested adjustments.