Image output method and device and user biological feature acquisition method and device

Abstract

The invention provides an image output method and device and a user biological characteristic acquisition method and device. The image output method comprises the steps of determining a quality evaluation result of an image acquired by a camera through an image quality decision model trained for biological health features; determining the image as an output image in response to the condition that the quality evaluation result meets the condition; in response to the condition that the quality evaluation result does not meet the condition, adjusting parameters of the camera at least once based on the quality evaluation result, and determining a quality evaluation result of an adjusted image acquired by the adjusted camera through an image quality decision model after each adjustment; and in response to the condition that an adjustment quality evaluation result of the adjusted image meets the condition, determining the adjusted image as an output image. The user biological health feature acquisition method comprises the following steps: acquiring a user image obtained by using the image output method in the disclosure; and determining biological health features of the user based on the user image.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology. More specifically, the present disclosure relates to an image output method and device and a user biometric feature acquisition method and device. Background Art

[0002] With the development of economy and health, heart rate estimation and detection are very important for a person's physiological and psychological state. Traditional methods of measuring heart rate are contact-based, such as electrode electrocardiogram, which measures heart rate by sensing the human body's cardiac current through electrodes; on wearable devices such as smart watches, the most commonly used method is to use photoelectric volume pulse wave (PPG) for measurement, but it also requires close contact with the skin. Although the contact measurement method is more accurate, it will inevitably bring a lot of discomfort and inconvenience, especially in some special scenarios, non-contact solutions have great advantages. Summary of the invention

[0003] According to an exemplary embodiment of the present disclosure, there is provided an image output method, comprising: determining a quality assessment result of an image acquired by a camera through an image quality decision model trained for biological health features; in response to the quality assessment result satisfying a condition, determining the image as an output image; in response to the quality assessment result not satisfying the condition, adjusting the parameters of the camera at least once based on the quality assessment result, and determining a quality assessment result of an adjusted image acquired by the adjusted camera through the image quality decision model after each adjustment; in response to the adjusted quality assessment result of the adjusted image satisfying the condition, determining the adjusted image as an output image.

[0004] Optionally, the quality assessment result may include at least one of a brightness assessment result, a signal quality assessment result and a motion assessment result.

[0005] Optionally, adjusting the parameters of the camera based on the quality assessment result may include: adjusting brightness-related parameters of the camera based on the brightness assessment result being less than a brightness threshold, wherein the brightness-related parameters include at least one of sensitivity, exposure, and white balance; adjusting signal quality-related parameters of the camera based on the signal quality assessment result being less than a signal quality threshold, wherein the signal quality-related parameters include at least one of zoom, resolution, and frame rate; adjusting motion-related parameters of the camera based on the motion assessment result being less than a motion threshold, wherein the motion-related parameters include shutter speed.

[0006] Optionally, adjusting the brightness-related parameters of the camera may include: increasing at least one of the sensitivity, exposure and white balance of the camera by a predetermined amount or increasing it to a next level; adjusting the brightness-related parameters of the camera may include: increasing at least one of the zoom, resolution and frame rate of the camera by a predetermined amount or increasing it to a next level; adjusting the motion-related parameters of the camera may include: increasing the shutter speed of the camera by a predetermined amount or increasing it to a next level.

[0007] Optionally, the image output method may further include: outputting prompt information for improving the shooting environment or shooting quality based on the number of times the adjustment is performed being equal to a threshold of the number of times of adjustment or the parameter being adjusted to a maximum value.

[0008] Optionally, the image quality decision model can be trained by the following operations: training the initial health measurement model using a standard environment data set to obtain parameters of the trained health measurement model, wherein the standard environment data set includes a first image of each training object among multiple training objects under a standard environment, real health data of the first image, environmental parameters and camera parameters; updating the parameters of the initial image quality decision model based on the parameters of the trained health measurement model; training the initial image quality decision model with updated parameters using a real environment data set, and using the trained image quality decision model as the final image quality decision model, wherein the real environment data set includes a second image of each training object among multiple training objects under multiple different real environments, real quality score data of the second image, environmental parameters and camera parameters.

[0009] Optionally, the training of the initial health measurement model using a standard environment data set may include: inputting the standard environment data set into the initial health measurement model to obtain health measurement data output by the initial health measurement model; calculating the difference between the health measurement data and the true health data as a first training loss; and adjusting the parameters of the initial health measurement model according to the first training loss.

[0010] Optionally, the training of the parameter-updated initial image quality decision model using the real environment dataset may include: inputting the real environment dataset into the parameter-updated initial image quality decision model to obtain image quality score data output by the parameter-updated initial image quality decision model; calculating the difference between the image quality score data and the real image quality score data as a second training loss; and adjusting the parameters of the parameter-updated initial health measurement model according to the second training loss.

[0011] According to an exemplary embodiment of the present disclosure, a method for acquiring a user's biological health characteristics is provided, comprising: acquiring a user image, wherein the user image is an output image obtained using the image output method of the present disclosure; and determining the user's biological health characteristics based on the user image.

[0012] According to an exemplary embodiment of the present disclosure, there is provided an image output device, comprising: a quality assessment unit, configured to determine a quality assessment result of an image acquired by a camera through an image quality decision model trained for biological health features; an output image determination unit, configured to determine the image as an output image in response to the quality assessment result satisfying a condition; a loop execution unit, configured to adjust the parameters of the camera at least once based on the quality assessment result in response to the quality assessment result not satisfying the condition, and determine the quality assessment result of an adjusted image acquired by the adjusted camera through the image quality decision model after each adjustment, wherein the output image determination unit is further configured to determine the adjusted image as the output image in response to the quality assessment result of the adjusted image satisfying the condition.

[0013] Optionally, the quality assessment result may include at least one of a brightness assessment result, a signal quality assessment result and a motion assessment result.

[0014] Optionally, the loop execution unit may be configured to: adjust brightness-related parameters of the camera based on the brightness evaluation result being less than a brightness threshold, wherein the brightness-related parameters include at least one of sensitivity, exposure, and white balance; adjust signal quality-related parameters of the camera based on the signal quality evaluation result being less than a signal quality threshold, wherein the signal quality-related parameters include at least one of zoom, resolution, and frame rate; and adjust motion-related parameters of the camera based on the motion evaluation result being less than a motion threshold, wherein the motion-related parameters include shutter speed.

[0015] Optionally, the loop execution unit may be configured to increase at least one of the sensitivity, exposure and white balance of the camera by a predetermined amount or to a next level, the loop execution unit may be configured to increase at least one of the zoom, resolution and frame rate of the camera by a predetermined amount or to a next level, and the loop execution unit may be configured to increase the shutter speed of the camera by a predetermined amount or to a next level.

[0016] Optionally, the image output device may further include: a prompt output unit configured to output prompt information for improving the shooting environment or shooting quality based on the number of times the adjustment is performed being equal to the adjustment number threshold or the parameter being adjusted to a maximum value.

[0017] Optionally, the image quality decision model can be trained by the following operations: training the initial health measurement model using a standard environment data set to obtain parameters of the trained health measurement model, wherein the standard environment data set includes a first image of each training object among multiple training objects under a standard environment, real health data of the first image, environmental parameters and camera parameters; updating the parameters of the initial image quality decision model based on the parameters of the trained health measurement model; training the initial image quality decision model with updated parameters using a real environment data set, and using the trained image quality decision model as the final image quality decision model, wherein the real environment data set includes a second image of each training object among multiple training objects under multiple different real environments, real quality score data of the second image, environmental parameters and camera parameters.

[0018] Optionally, the training of the initial health measurement model using a standard environment data set may include: inputting the standard environment data set into the initial health measurement model to obtain health measurement data output by the initial health measurement model; calculating the difference between the health measurement data and the true health data as a first training loss; and adjusting the parameters of the initial health measurement model according to the first training loss.

[0019] Optionally, the training of the parameter-updated initial image quality decision model using the real environment dataset may include: inputting the real environment dataset into the parameter-updated initial image quality decision model to obtain image quality score data output by the parameter-updated initial image quality decision model; calculating the difference between the image quality score data and the real image quality score data as a second training loss; and adjusting the parameters of the parameter-updated initial health measurement model according to the second training loss.

[0020] According to an exemplary embodiment of the present disclosure, a device for acquiring a user's biological health characteristics is provided, comprising: an image acquisition unit, configured to acquire a user image, wherein the user image is an output image obtained using the image output method of the present disclosure; and a health characteristic determination unit, configured to determine the user's biological health characteristics based on the user image.

[0021] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, an image output method or a user biometric acquisition method according to an exemplary embodiment of the present disclosure is implemented.

[0022] According to an exemplary embodiment of the present disclosure, there is provided a computing device, comprising: at least one processor; and at least one memory storing a computer program, wherein when the computer program is executed by the at least one processor, an image output method or a user biometric acquisition method according to an exemplary embodiment of the present disclosure is implemented.

[0023] According to an exemplary embodiment of the present disclosure, a computer program product is provided, and instructions in the computer program product can be executed by a processor of a computer device to complete the image output method or the user biometric feature acquisition method according to the exemplary embodiment of the present disclosure.

[0024] According to the image output method and device of the exemplary embodiments of the present disclosure, a quality assessment result of an image acquired by a camera is determined by an image quality decision model trained for biological health features. In response to the quality assessment result satisfying a condition, the image is determined as an output image. In response to the quality assessment result not satisfying the condition, the parameters of the camera are adjusted at least once based on the quality assessment result. After each adjustment, a quality assessment result of an adjusted image acquired by the adjusted camera is determined by the image quality decision model. In response to the adjusted quality assessment result of the adjusted image satisfying the condition, the adjusted image is determined as an output image, thereby improving the effect of acquiring images.

[0025] According to the user biometrics acquisition method and device of the exemplary embodiments of the present disclosure, a user image is acquired, wherein the user image is an output image obtained using the image output method of the present disclosure, and the user's biometric health characteristics are determined based on the user image, thereby improving the accuracy of the user's biometric health characteristics.

[0026] Additional aspects and / or advantages of the present general inventive concept will be set forth in part in the following description and in part will be apparent from the description or may be learned through practice of the present general inventive concept. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and other objects and features of the exemplary embodiments of the present disclosure will become more apparent through the following description in conjunction with the accompanying drawings which exemplarily illustrate the embodiments, in which: Figure 1 A flowchart showing an image output method according to an exemplary embodiment of the present disclosure; Figure 2 A schematic diagram showing a training image quality decision model according to an exemplary embodiment of the present disclosure; Figure 3 An example of adjusting a signal quality evaluation result in a quality evaluation result by adjusting a width of a face frame in an image according to an exemplary embodiment of the present disclosure is shown; Figure 4 A flowchart showing a method for acquiring a user's biometric health characteristics according to an exemplary embodiment of the present disclosure; Figure 5 An example of obtaining a user's biometric health feature by adjusting a signal quality-related parameter of a camera according to an exemplary embodiment of the present disclosure is shown; Figure 6 An example of obtaining a user's biometric health feature by adjusting a brightness-related parameter of a camera according to an exemplary embodiment of the present disclosure is shown; Figure 7 An example of obtaining a user's biometric health characteristics by adjusting a motion-related parameter of a camera according to an exemplary embodiment of the present disclosure is shown; Figure 8 An example of obtaining a user's biometric health feature by adjusting a brightness-related parameter of a camera according to an exemplary embodiment of the present disclosure is shown; Fig. 9 An example of outputting prompt information to a user according to an exemplary embodiment of the present disclosure is shown; Fig.10 A block diagram showing an image output device according to an exemplary embodiment of the present disclosure; Fig.11 A block diagram showing a user biometric health feature acquisition device according to an exemplary embodiment of the present disclosure; and Fig.12 A schematic diagram illustrating a computing device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Reference will now be made in detail to exemplary embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein like reference numerals refer to like parts throughout. The embodiments will be described below with reference to the drawings in order to explain the present disclosure.

[0029] Figure 1 A flowchart illustrating an image output method according to an exemplary embodiment of the present disclosure is shown. Figure 2 A schematic diagram showing a training image quality decision model according to an exemplary embodiment of the present disclosure is shown. Figure 1 The image output method in the present invention can be applied to various electronic devices with cameras such as televisions or mobile phones. Figure 1 The image output by the image output method in the present disclosure can make the measurement of the user's heart rate more accurate. In the present disclosure, the image can be a video frame. The electronic device can obtain a video including an image of a user who is using the electronic device. The image output method of the present disclosure can be used to perform quality assessment on one or more video frames of the video and output video frames that meet conditions. The image output method of the present disclosure can be used to perform quality assessment on a video frame of the video and output the video frame when conditions are met.

[0030] Reference Figure 1 In step S101, the quality assessment result of the image acquired by the camera is determined by the image quality decision model trained for the biological health features. Here, the image quality assessment is performed by introducing the image quality decision model trained for the biological health features to improve the efficiency of the image quality assessment. Before the image is quantitatively assessed, the image may be processed, for example, but not limited to, white balance processing, color correction, etc. Thereafter, the face region is acquired from the processed image. For example, various existing face detection and tracking schemes may be used. According to the face region, a focus region (e.g., ROI region) may be set, and face alignment may be performed.

[0031] In an exemplary embodiment of the present disclosure, the quality assessment result may include at least one of a brightness assessment result, a signal quality assessment result, and a motion assessment result, thereby improving the effectiveness of image quality assessment by defining three aspects of image quality assessment (e.g., brightness, signal quality, and motion).

[0032] In an exemplary embodiment of the present disclosure, the image quality decision model may be obtained by training through the following operations: training the initial health measurement model using a standard environment data set to obtain parameters of the trained health measurement model, wherein the standard environment data set includes a first image of each training object in a plurality of training objects under a standard environment, real health data of the first image, environmental parameters, and camera parameters; updating the parameters of the initial image quality decision model based on the parameters of the trained health measurement model; training the parameter-updated initial image quality decision model using a real environment data set, and using the trained image quality decision model as the final image quality decision model, wherein the real environment data set includes a second image of each training object in a plurality of training objects under a plurality of different real environments, real quality score data of the second image, environmental parameters, and camera parameters. Updating the parameters of the initial image quality decision model based on the parameters of the trained health measurement model may include: sharing the parameters of the trained health measurement model in the first step training result with the initial image quality decision model in the second step training. By sharing the parameters of the trained health measurement model in the first step training result with the initial image quality decision model in the second step training, the image quality decision model is guided to focus on the skin color area instead of the global features, thereby improving the accuracy of the image quality decision.

[0033] In an exemplary embodiment of the present disclosure, the environmental parameters may include light environment parameters and motion parameters, and the camera parameters may include at least one of shutter speed, sensitivity, exposure and white balance, zoom, resolution and frame rate.

[0034] In an exemplary embodiment of the present disclosure, the standard environment data set may be an image data set acquired under a standard configuration environment. The standard environment data set is a small-scale data set used for the first step of training. The standard environment data set will be collected under an optimal environment adjusted manually. For example, the standard environment data set may be an image data set acquired under the following environment: (1) the light environment parameters are different light environments within the range of 500-400 lux set according to different skin colors; (2) the motion parameters are that the measurement personnel remain still and at rest; (3) the camera parameters are parameters such as ISO and shutter of the camera adjusted according to the light and skin color to achieve the best shooting conditions.

[0035] In an exemplary embodiment of the present disclosure, the real environment dataset may be an image dataset acquired in a real configuration environment. The real environment dataset is a large-scale dataset used for the second step training, and the real environment dataset is collected from a real world environment, including various cameras and light environment videos. For example, the real environment dataset may be an image dataset acquired in the current real environment.

[0036] In an exemplary embodiment of the present disclosure, training an initial health measurement model using a standard environment data set may include: inputting the standard environment data set into the initial health measurement model to obtain health measurement data output by the initial health measurement model; calculating the difference between the health measurement data and the real health data as a first training loss; and adjusting the parameters of the initial health measurement model according to the first training loss. Here, the health measurement data may include data on at least one of heart rate (HR), heart rate variability (HRV), blood oxygen saturation (SPO2), and respiratory rate (RR).

[0037] In an exemplary embodiment of the present disclosure, training the parameter-updated initial image quality decision model using a real environment dataset may include: inputting the real environment dataset into the parameter-updated initial image quality decision model to obtain image quality score data output by the parameter-updated initial image quality decision model; calculating the difference between the image quality score data and the real image quality score data as a second training loss; and adjusting the parameters of the parameter-updated initial health measurement model according to the second training loss.

[0038] As an example, Figure 2As shown, the image quality decision model is trained by a two-step training method. In the first step of training, the standard environment data set is input into the initial health measurement model to obtain the health measurement data output by the initial health measurement model, the difference between the health measurement data and the real health data in the standard environment data set is calculated as the first training loss, and the parameters of the initial health measurement model are adjusted according to the first training loss. The initial health measurement model first performs facial ROI recognition on the image in the standard environment data set, extracts features from the recognized facial ROI, and measures the health measurement data of the face based on the extracted features. A health measurement model (i.e., an expert network) can be trained from the standard environment data set to learn the skin color area with the best measurement results for different skin colors and distances. After the first step of training, the parameters of the trained health measurement model in the first step of training results are shared with the initial image quality decision model in the second step of training. In the second step of training, the real environment data set is input into the parameter-updated initial image quality decision model to obtain the image quality score data output by the parameter-updated initial image quality decision model; the difference between the image quality score data and the real image quality score data is calculated as the second training loss; and the parameters of the parameter-updated initial health measurement model are adjusted according to the second training loss. The initial image quality decision model is trained to estimate the correct measurement environment score, which includes brightness, signal quality and motion. The parameters of the trained healthy measurement model in the first step of training are shared with the initial image quality decision model in the second step of training. The initial image quality decision model is guided to focus on the results of the optimal skin color area through the attention layer, thereby obtaining results that are more consistent with Remote Photoplethysmography (RPPG) measurement.

[0039] In step S102, in response to the quality assessment result satisfying a condition, the image is determined as an output image.

[0040] In an exemplary embodiment of the present disclosure, if the quality assessment result meets the condition, it means that the quality of the image acquired by the camera is qualified. Here, the condition that the quality assessment result needs to meet may be within a predetermined or specified range, for example, but not limited to, greater than or equal to a threshold. As an example, in the case where the quality assessment result includes a brightness assessment result, a signal quality assessment result, and a motion assessment result, the condition that the quality assessment result needs to meet may be that the brightness assessment result, the signal quality assessment result, and the motion assessment result each meet the corresponding condition, for example, the brightness is greater than or equal to a brightness threshold, the signal quality is greater than or equal to a signal quality threshold, and the motion is greater than or equal to a motion threshold.

[0041] In step S103, in response to the quality evaluation result not satisfying the condition, the parameters of the camera are adjusted at least once based on the quality evaluation result, and after each adjustment, the quality evaluation result of the adjusted image acquired by the adjusted camera is determined by the image quality decision model. The parameters of the camera may be, for example, but not limited to, zoom (Zoom), sensitivity (ISO), white balance (White Balance, referred to as WB), shutter speed (Speed), exposure (Exposure Values, referred to as EV), resolution (Resolution), frame rate (Frame Rate) and other parameters.

[0042] In an exemplary embodiment of the present disclosure, adjusting the parameters of the camera based on the quality evaluation result may include: adjusting brightness-related parameters of the camera based on the brightness evaluation result being less than a brightness threshold, wherein the brightness-related parameters include at least one of sensitivity, exposure, and white balance; adjusting signal quality-related parameters of the camera based on the signal quality evaluation result being less than a signal quality threshold, wherein the signal quality-related parameters include at least one of zoom, resolution, and frame rate; adjusting motion-related parameters of the camera based on the motion evaluation result being less than a motion threshold, wherein the motion-related parameters include shutter speed, thereby improving the effect of parameter adjustment by adjusting the parameters corresponding to the items of the evaluation results that do not meet the standards.

[0043] In an exemplary embodiment of the present disclosure, adjusting the brightness-related parameters of the camera may include increasing at least one of the sensitivity, exposure, and white balance of the camera by a predetermined amount or to a next level.

[0044] In an exemplary embodiment of the present disclosure, adjusting the brightness-related parameters of the camera may include increasing at least one of zoom, resolution, and frame rate of the camera by a predetermined amount or to a next level.

[0045] In an exemplary embodiment of the present disclosure, adjusting the motion-related parameters of the camera may include increasing a shutter speed of the camera by a predetermined amount or to a next level.

[0046] In an exemplary embodiment of the present disclosure, when the parameters of the camera are adjusted at least once based on the quality assessment result, and after each adjustment, the quality assessment result of the adjusted image obtained by the adjusted camera is determined by the image quality decision model, the adjustment of the parameters of the camera and the determination of the quality assessment result of the adjusted image obtained by the adjusted camera can be repeated until the quality assessment result meets the condition; the final adjusted image is determined as the output image, so that in the case of poor image quality, the camera parameter adjustment is repeated multiple times to obtain an output image with quality that meets the requirements.

[0047] In an exemplary embodiment of the present disclosure, when the parameters of the camera are adjusted at least once based on the quality assessment result, the number of times the adjustment is performed can be determined; if the number of times the adjustment is performed is less than an adjustment number threshold, the parameters of the camera are adjusted, thereby setting the adjustment number threshold so that the parameters of the camera are adjusted only when the number of times the adjustment is performed is less than the adjustment number threshold, thereby determining as soon as possible that the image quality is not caused by the parameters of the camera.

[0048] In an exemplary embodiment of the present disclosure, when the parameters of the camera are adjusted at least once based on the quality assessment result, the parameters of the camera can be adjusted based on the adjustment quality assessment result of the previous adjustment of the current adjustment in each current adjustment, thereby improving the parameter adjustment effect by further specifically limiting that each repeated parameter adjustment is based on the adjustment quality assessment result of the previous adjustment of the current adjustment.

[0049] In step S104, in response to the quality evaluation result of the adjusted image satisfying the condition, the adjusted image is determined as an output image.

[0050] In an exemplary embodiment of the present disclosure, the image output method may further include: based on the number of times the adjustment is performed being equal to the repetition number threshold or the parameter being adjusted to the maximum value, outputting prompt information for improving the shooting environment or shooting quality, so that when it is determined that the image quality is not caused by the camera parameters, the user is prompted to promptly improve the shooting environment or shooting quality by outputting prompt information to improve the image acquisition efficiency. If the image quality evaluation score is still low after repeated adjustment of the parameters, the user may be prompted that the current environment is not sufficient to measure the heart rate and suggestions may be given, such as turning on the lights, exercising slower, etc.

[0051] Figure 3 An example of adjusting the signal quality evaluation result in the quality evaluation result by adjusting the width of the face frame in the image according to an exemplary embodiment of the present disclosure is shown. Each quality evaluation result includes a brightness evaluation result (e.g., Figure 3 brightness score in ), signal quality assessment results (e.g., Figure 3 signal quality scores in ) and motion assessment results (e.g., Figure 3 When the user is far away from the TV, the width of the face frame is smaller than the width threshold or pixel threshold (for example, Figure 3 40 pixels in the image), the signal quality assessment results (for example, Figure 3 The signal quality score in is less than the signal quality threshold (for example, Figure 3 In this case, the signal quality related parameters are adjusted repeatedly and then an image is acquired and the face region in the acquired image is input into the image quality decision model until the signal quality score is higher than the signal quality threshold (e.g., Figure 3 0.9 in ).

[0052] like Figure 3 As shown, in step S301, the quality of the image acquired by the camera for the first time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the first time is: brightness evaluation result (for example, Figure 3 The brightness score in ) is 0.94, and the signal quality assessment results (e.g., Figure 3 The signal quality score in ) is 0.80, and the motion evaluation results (e.g. Figure 3 In this case, it can be determined that the user is far away from the TV and the signal quality related parameters need to be adjusted, such as, but not limited to, Figure 3 In step S302, adjust the signal quality related parameters, such as the zoom parameter, such as Figure 3 As shown, the zoom parameter is adjusted from x1 to x2. In step S303, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 3 The brightness score in ) is 0.94, and the signal quality assessment results (e.g., Figure 3 The signal quality score in ) is 0.86, and the motion evaluation results (e.g. Figure 3 In this case, it can be determined that the signal quality related parameters have not been adjusted to a suitable value, so it is necessary to continue to adjust the signal quality related parameters, such as, but not limited to, Figure 3 In step S304, adjust the signal quality related parameters, such as the zoom parameter, such as Figure 3As shown, the zoom parameter is adjusted from x2 to x3. In step S305, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 3 The brightness score in ) is 0.94, and the signal quality assessment results (e.g., Figure 3 The signal quality score in ) is 0.91, and the motion evaluation results (e.g. Figure 3 In this case, it can be determined that the signal quality related parameters have been adjusted to appropriate values, and the image at this time is determined as the output image.

[0053] Figure 4 A flow chart of a method for acquiring a user's biometric health characteristics according to an exemplary embodiment of the present disclosure is shown. Figure 4 The method for acquiring user biometric health characteristics in the present invention can be applied to an electronic device having a camera and a processor.

[0054] Reference Figure 4 In step S401, a user image is obtained, wherein the user image is an output image obtained using the image output method in the present disclosure.

[0055] In step S402, a user's biological health characteristics are determined based on the user image.

[0056] In an exemplary embodiment of the present disclosure, the user's bio-health characteristics may include at least one of heart rate (HR), heart rate variability (HRV), blood oxygen saturation (SPO2) and respiratory rate (RR).

[0057] Figure 5 An example of obtaining a user's biometric health feature by adjusting a signal quality-related parameter of a camera according to an exemplary embodiment of the present disclosure is shown. Each quality evaluation result includes a brightness evaluation result (e.g., Figure 5 brightness score in ), signal quality assessment results (e.g., Figure 5 signal quality scores in ) and motion assessment results (e.g., Figure 5 sports scores in ).

[0058] like Figure 5 As shown, the brightness of the current environment is normal, the user is 4 meters away from the TV, the user is not moving quickly, and the user's skin color is yellow. Since the user is far away from the TV, the width of the user's face frame in the acquired image is relatively small. In step S501, the quality of the image acquired by the camera for the first time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the first time is: brightness evaluation result (for example, Figure 5The brightness score in ) is 0.94, and the signal quality assessment results (e.g., Figure 5 The signal quality score in ) is 0.80, and the motion evaluation results (e.g. Figure 5 In this case, it can be determined that the user is far away from the TV and the signal quality related parameters need to be adjusted (for example, but not limited to, Figure 5 In step S502, adjust the signal quality related parameters (for example, the zoom parameter), such as Figure 5 As shown, the zoom parameter is adjusted from x1 to x2. In step S503, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 5 The brightness score in ) is 0.94, and the signal quality assessment results (e.g., Figure 5 The signal quality score in ) is 0.86, and the motion evaluation results (e.g. Figure 5 In this case, it can be determined that the signal quality related parameters have not been adjusted to a suitable value, so it is necessary to continue to adjust the signal quality related parameters (for example, but not limited to, Figure 5 In step S504, adjust the signal quality related parameters (eg, zoom parameters), such as Figure 5 As shown, the zoom parameter is adjusted from x2 to x3. In step S505, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 5 The brightness score in ) is 0.94, and the signal quality assessment results (e.g., Figure 5 The signal quality score in ) is 0.91, and the motion evaluation results (e.g. Figure 5 In this case, it can be determined that the signal quality related parameters have been adjusted to appropriate values, and the user's biological health characteristics are determined based on the image at this time: HR is 67, HRV is 60, SPO2 is 99, and RR is 20.

[0059] In the related art, without image quality assessment and parameter adjustment, Figure 5 When the user's bio-health characteristics are determined directly based on the image in the environment shown, the obtained user's bio-health characteristics (HR is 75, HRV is 67, SPO2 is 95, RR is 25) are inaccurate.

[0060] Figure 6An example of obtaining a user's biometric health feature by adjusting a brightness-related parameter of a camera according to an exemplary embodiment of the present disclosure is shown. Each quality assessment result includes a brightness assessment result (e.g., Figure 6 brightness score in ), signal quality assessment results (e.g., Figure 6 signal quality scores in ) and motion assessment results (e.g., Figure 6 sports scores in ).

[0061] like Figure 6 As shown, the current environment brightness is dim, the user is 1 to 2 meters away from the TV, the user is not moving quickly, and the user's skin color is white. In step S601, the quality of the image acquired by the camera for the first time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the first time is: brightness evaluation result (for example, Figure 6 The brightness score in the image is 0.65, and the signal quality assessment results (e.g., Figure 6 The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Figure 6 In this case, it can be determined that the current environment brightness is low and it is necessary to adjust brightness-related parameters (for example, but not limited to, Figure 6 In step S602, brightness-related parameters (e.g., sensitivity (ISO) parameters and exposure (EV) parameters) are adjusted, such as Figure 6 As shown, the sensitivity (ISO) parameter is adjusted from 750 to 800, and the exposure (EV) parameter is increased by 1.0EV. In step S603, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 6 The brightness score in the image is 0.7, and the signal quality assessment results (e.g., Figure 6 The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Figure 6 In this case, it can be determined that the brightness-related parameters have not been adjusted to a suitable value, so it is necessary to continue to adjust the brightness-related parameters (for example, but not limited to, Figure 6 In step S604, adjust brightness-related parameters (e.g., sensitivity (ISO) parameters and exposure (EV) parameters). In step S605, perform quality assessment on the image acquired by the camera for the second time to obtain a quality assessment result. For example, the quality assessment result of the image acquired by the camera for the second time is: brightness assessment result (e.g., Figure 6 The brightness score in ) is 0.91, and the signal quality assessment results (e.g., Figure 6 The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Figure 6 In this case, it can be determined that the brightness-related parameters have been adjusted to appropriate values, and the user's biological health characteristics are determined based on the image at this time: HR is 66, HRV is 60, SPO2 is 99, and RR is 22.

[0062] In the related art, without image quality assessment and parameter adjustment, Figure 6 When the user's bio-health characteristics are determined directly based on the image in the environment shown, the obtained user's bio-health characteristics (HR is 60, HRV is 78, SPO2 is 99, and RR is 16) are inaccurate.

[0063] Figure 7 An example of obtaining a user's biometric health feature by adjusting the motion-related parameters of a camera according to an exemplary embodiment of the present disclosure is shown. Each quality assessment result includes a brightness assessment result (e.g., Figure 7 brightness score in ), signal quality assessment results (e.g., Figure 7 signal quality scores in ) and motion assessment results (e.g., Figure 7 sports scores in ).

[0064] like Figure 7 As shown, the indoor environment brightness is normal, the user is 1 to 2 meters away from the TV, the user is moving, and the user's skin color is white. In step S701, the quality of the image acquired by the camera for the first time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the first time is: brightness evaluation result (for example, Figure 7 The brightness score in the image is 0.95, and the signal quality assessment results (e.g., Figure 7 The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Figure 7 In this case, it can be determined that the motion score is too low and the motion-related parameters need to be adjusted (for example, but not limited to, Figure 7 In step S702, the motion-related parameters (eg, shutter speed (Speed) parameters) are adjusted, such as Figure 7 As shown, the shutter speed (Speed) parameter is adjusted from 1 / 60 to 1 / 70. In step S703, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 7 The brightness score in the image is 0.95, and the signal quality assessment results (e.g., Figure 7The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Figure 7 In this case, it can be determined that the motion-related parameters have not been adjusted to a suitable value, and therefore the motion-related parameters need to be further adjusted (for example, but not limited to, Figure 7 In step S704, the motion-related parameters (eg, shutter speed (Speed) parameters) are adjusted, such as Figure 7 As shown, the shutter speed (Speed) parameter is adjusted from 1 / 70 to 1 / 80. In step S705, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 7 The brightness score in the image is 0.95, and the signal quality assessment results (e.g., Figure 7 The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Figure 7 In this case, it can be determined that the exercise-related parameters have been adjusted to appropriate values, and the user's biological health characteristics are determined based on the image at this time: HR is 120, HRV is 93, SPO2 is 97, and RR is 60.

[0065] In the related art, without image quality assessment and parameter adjustment, Figure 7 When the user's bio-health characteristics are determined directly based on the image in the environment shown, the obtained user's bio-health characteristics (HR is 111, HRV is 100, SPO2 is 99, RR is 70) are inaccurate.

[0066] Figure 8 An example of obtaining a user's biometric health feature by adjusting a brightness-related parameter of a camera according to an exemplary embodiment of the present disclosure is shown. Each quality assessment result includes a brightness assessment result (e.g., Figure 8 brightness score in ), signal quality assessment results (e.g., Figure 8 signal quality scores in ) and motion assessment results (e.g., Figure 8 sports scores in ).

[0067] like Figure 8 As shown, the indoor environment brightness is normal, the user is 1 to 2 meters away from the TV, the user is not moving quickly, and the user's skin color is black. In step S801, the quality of the image acquired by the camera for the first time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the first time is: brightness evaluation result (for example, Figure 8 The brightness score in the image is 0.75, and the signal quality assessment results (e.g., Figure 8The signal quality score in ) is 0.83, and the motion evaluation results (e.g. Figure 8 In this case, it can be determined that the user has dark skin and the brightness score is low, and it is necessary to adjust the brightness related parameters (such as, but not limited to, Figure 6 sensitivity (ISO) parameters and exposure value (EV) parameters in the Figure 8 In step S802, brightness related parameters (eg, sensitivity (ISO) parameters and exposure (EV) parameters) are adjusted, such as Figure 8 As shown, the sensitivity (ISO) parameter is adjusted from 800 to 850, and the exposure (EV) parameter is increased by 1.0EV. In step S803, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 8 The brightness score in ) is 0.91, and the signal quality assessment results (e.g., Figure 8 The signal quality score in ) is 0.83, and the motion evaluation results (e.g. Figure 8 In step S804, the signal quality related parameters (eg, zoom parameters) are adjusted, such as Figure 8 As shown, the zoom parameter is adjusted from x1 to x2. In step S805, the quality of the image acquired by the camera for the second time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the second time is: brightness evaluation result (for example, Figure 8 The brightness score in ) is 0.91, and the signal quality assessment results (e.g., Figure 8 The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Figure 8 In this case, it can be determined that the signal quality related parameters have been adjusted to appropriate values, and the user's biological health characteristics are determined based on the image at this time: HR is 67, HRV is 59, SPO2 is 96, and RR is 22.

[0068] In the related art, without image quality assessment and parameter adjustment, Figure 8 When the user's biometric health characteristics are determined directly based on the image in the environment shown, the obtained user's biometric health characteristics (HR is 62, HRV is 67, SPO2 is 92, and RR is 18) are inaccurate.

[0069] Fig. 9 An example of outputting prompt information to a user according to an exemplary embodiment of the present disclosure is shown. Each quality evaluation result includes a brightness evaluation result (eg, Fig. 9 brightness score in ), signal quality assessment results (e.g., Fig. 9 signal quality scores in ) and motion assessment results (e.g., Fig. 9 sports scores in ).

[0070] like Fig. 9 As shown, the current environment brightness is dim, the user is 1 to 2 meters away from the TV, the user is not moving quickly, and the user's skin color is black. In step S901, the quality of the image acquired by the camera for the first time is evaluated to obtain a quality evaluation result. For example, the quality evaluation result of the image acquired by the camera for the first time is: brightness evaluation result (for example, Fig. 9 The brightness score in the image is 0.55, and the signal quality assessment results (e.g., Fig. 9 The signal quality score in ) is 0.93, and the motion evaluation results (e.g. Fig. 9 In this case, it can be determined that the ambient brightness is dim and the brightness-related parameters (e.g., sensitivity (ISO) parameter and exposure (EV) parameter) need to be adjusted. In steps S902 to S905, the brightness-related parameters are repeatedly adjusted until all the brightness-related parameters are adjusted to the maximum value. The brightness evaluation result (e.g., Fig. 9 In step S906, a prompt message "It's too dark, please turn on the light" is output to increase the brightness of the current environment, so as to obtain a suitable image to determine the user's biological health characteristics.

[0071] In addition, when the signal quality score or the motion score cannot be satisfied after repeated adjustments, the user may be prompted to move slower or get closer to the TV.

[0072] The present disclosure provides a method for obtaining health data more accurately. By adjusting the camera parameters, more accurate image data can be obtained, thereby obtaining more accurate health data (for example, but not limited to HR, HRV, SPO2 and RR, etc.). The present disclosure overcomes the shortcomings of the prior art and provides a camera in remote photoplethysmography (RGGP) mode. Through an image quality assessment method, it effectively avoids inaccurate heart rate measurement in some undesirable conditions (for example, insufficient light, long distance, the user being a person of color, and repeated adjustments that cannot reach the ideal state), thereby improving the accuracy of the user's heart rate measurement.

[0073] The above has been combined Figures 1 to 9 The image output method and the user biometric health feature acquisition method according to the exemplary embodiment of the present disclosure are described. Fig.10 and Fig.11An image output device and its units, and a user biometric health feature acquisition device and its units according to exemplary embodiments of the present disclosure are described.

[0074] Fig.10 A block diagram illustrating an image output device according to an exemplary embodiment of the present disclosure.

[0075] Reference Fig.10 The image output device includes a quality assessment unit 101, an output image determination unit 102 and a loop execution unit 103. The quality assessment unit 101 is configured to determine a quality assessment result of an image acquired by a camera through an image quality decision model trained for biological health features.

[0076] In an exemplary embodiment of the present disclosure, the quality evaluation result may include at least one of a brightness evaluation result, a signal quality evaluation result, and a motion evaluation result.

[0077] In an exemplary embodiment of the present disclosure, the image quality decision model can be trained by the following operations: using a standard environment data set to train an initialization model to obtain an intermediate model, wherein the standard environment data set includes images of each training object among multiple training objects under a standard environment, feature parameters of the images, and quality assessment data of the images; using a real environment data set to train the intermediate model to obtain an image quality decision model, wherein the real environment data set includes images of each training object among multiple training objects under a variety of different real environments, feature parameters of the images, and quality assessment data of the images.

[0078] The output image determining unit 102 is configured to determine the image as an output image in response to the quality assessment result satisfying a condition.

[0079] In an exemplary embodiment of the present disclosure, the output image determining unit 102 may be further configured to determine the adjusted image as the output image in response to the quality evaluation result of the adjusted image satisfying the condition.

[0080] The loop execution unit 103 is configured to, in response to the quality assessment result not satisfying the condition, adjust the parameters of the camera at least once based on the quality assessment result, and determine the quality assessment result of the adjusted image acquired by the adjusted camera through the image quality decision model after each adjustment.

[0081] In an exemplary embodiment of the present disclosure, the loop execution unit 103 may be configured to: adjust the brightness-related parameters of the camera based on the brightness evaluation result being less than a brightness threshold, wherein the brightness-related parameters include at least one of sensitivity, exposure, and white balance; adjust the signal quality-related parameters of the camera based on the signal quality evaluation result being less than a signal quality threshold, wherein the signal quality-related parameters include at least one of zoom, resolution, and frame rate; and adjust the motion-related parameters of the camera based on the motion evaluation result being less than a motion threshold, wherein the motion-related parameters include shutter speed.

[0082] In an exemplary embodiment of the present disclosure, the loop execution unit 103 may also be configured to: increase at least one of the sensitivity, exposure and white balance of the camera by a predetermined amount or to a next level, the loop execution unit is configured to: increase at least one of the zoom, resolution and frame rate of the camera by a predetermined amount or to a next level, and the loop execution unit is configured to: increase the shutter speed of the camera by a predetermined amount or to a next level.

[0083] In an exemplary embodiment of the present disclosure, the image output device further includes: a prompt output unit (not shown) configured to output prompt information for improving the shooting environment or shooting quality based on the number of times the adjustment is performed being equal to the adjustment number threshold or the parameter being adjusted to the maximum value.

[0084] Fig.11 A block diagram of a device for acquiring a user's biological health characteristics according to an exemplary embodiment of the present disclosure is shown.

[0085] Reference Fig.11 The user biological health feature acquisition device includes an image acquisition unit 111 and a health feature determination unit 112.

[0086] The image acquisition unit 111 is configured to acquire a user image, wherein the user image is an output image obtained using the image output method in the present disclosure.

[0087] The health characteristic determination unit 112 is configured to determine a user's biological health characteristic based on the user image.

[0088] In an exemplary embodiment of the present disclosure, the user's bio-health characteristics may include at least one of heart rate, heart rate variability, blood oxygen saturation, and respiratory rate.

[0089] In addition, according to an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed, the image output method or the user biometric acquisition method according to the exemplary embodiment of the present disclosure is implemented.

[0090] In an exemplary embodiment of the present disclosure, the computer-readable storage medium may carry one or more programs, and when the computer program is executed, the following steps can be implemented: determining a quality assessment result of an image acquired by a camera through an image quality decision model trained for biological health features; in response to the quality assessment result satisfying a condition, determining the image as an output image; in response to the quality assessment result not satisfying the condition, adjusting the parameters of the camera at least once based on the quality assessment result, and determining the quality assessment result of an adjusted image acquired by the adjusted camera through the image quality decision model after each adjustment; in response to the adjusted quality assessment result of the adjusted image satisfying the condition, determining the adjusted image as an output image.

[0091] In an exemplary embodiment of the present disclosure, the computer-readable storage medium may carry one or more programs, and when the computer program is executed, the following steps can be implemented: obtaining a user image, wherein the user image is an output image obtained using the image output method in the present disclosure; and determining the user's biological health characteristics based on the user image.

[0092] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a computer program that may be used by or in conjunction with an instruction execution system, device or device. The computer program contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof. The computer-readable storage medium may be contained in any device; it may also exist alone without being assembled into the device.

[0093] In addition, according to an exemplary embodiment of the present disclosure, a computer program product is also provided, and instructions in the computer program product can be executed by a processor of a computer device to complete the image output method or user biometric acquisition method according to an exemplary embodiment of the present disclosure.

[0094] The above has been combined Figure 10 to Figure 11The image output device and the user biometrics acquisition device according to the exemplary embodiments of the present disclosure are described. Fig.12 A computing device according to an exemplary embodiment of the present disclosure is described.

[0095] Fig.12 A schematic diagram illustrating a computing device according to an exemplary embodiment of the present disclosure.

[0096] Reference Fig.12 According to the exemplary embodiment of the present disclosure, the computing device 12 includes a memory 121 and a processor 122. The memory 121 stores a computer program. When the computer program is executed by the processor 122, the image output method or the user biometric acquisition method according to the exemplary embodiment of the present disclosure is implemented.

[0097] In an exemplary embodiment of the present disclosure, when the computer program is executed by the processor 122, the following steps can be implemented: determining a quality assessment result of an image acquired by a camera through an image quality decision model trained for biological health features; in response to the quality assessment result satisfying a condition, determining the image as an output image; in response to the quality assessment result not satisfying the condition, adjusting the parameters of the camera at least once based on the quality assessment result, and determining a quality assessment result of an adjusted image acquired by the adjusted camera through the image quality decision model after each adjustment; in response to the adjusted quality assessment result of the adjusted image satisfying the condition, determining the adjusted image as an output image.

[0098] In an exemplary embodiment of the present disclosure, when the computer program is executed by the processor 122, the following steps can be implemented: acquiring a user image, wherein the user image is an output image obtained using the image output method in the present disclosure; and determining the user's biological health characteristics based on the user image.

[0099] The computing device in the embodiments of the present disclosure may include, but is not limited to, devices such as mobile phones, laptop computers, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, and the like. Fig.12 The computing device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0100] The above has been referred to Figures 1 to 12 The image output method and device, and the user biometric acquisition method and device according to the exemplary embodiments of the present disclosure are described. However, it should be understood that: Figure 10 to Figure 11 The image output device and its units, the user biometric feature acquisition device and its units shown in the figure may be respectively configured as software, hardware, firmware or any combination of the above items to perform specific functions. Fig.12The computing device shown in is not limited to including the components shown above, but some components may be added or deleted as needed, and the above components may also be combined.

[0101] According to the image output method and device of the exemplary embodiments of the present disclosure, a quality assessment result of an image acquired by a camera is determined by an image quality decision model trained for biological health features. In response to the quality assessment result satisfying a condition, the image is determined as an output image. In response to the quality assessment result not satisfying the condition, the parameters of the camera are adjusted at least once based on the quality assessment result. After each adjustment, a quality assessment result of an adjusted image acquired by the adjusted camera is determined by the image quality decision model. In response to the adjusted quality assessment result of the adjusted image satisfying the condition, the adjusted image is determined as an output image, thereby improving the effect of acquiring images.

[0102] According to the user biometrics acquisition method and device of the exemplary embodiments of the present disclosure, a user image is acquired, wherein the user image is an output image obtained using the image output method of the present disclosure, and the user's biometric health characteristics are determined based on the user image, thereby improving the accuracy of the user's biometric health characteristics.

[0103] While the present disclosure has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure as defined by the following claims.

Claims

1. An image output method, comprising: determining a quality assessment result of an image acquired by a camera through an image quality decision model trained for biological health features; In response to the quality assessment result satisfying a condition, determining the image as an output image; In response to the quality assessment result not satisfying the condition, adjusting the parameters of the camera at least once based on the quality assessment result, and determining the quality assessment result of an adjusted image acquired by the adjusted camera through an image quality decision model after each adjustment; in response to the quality assessment result of the adjusted image satisfying the condition, determining the adjusted image as an output image.

2. The image output method according to claim 1, wherein: The quality evaluation result includes at least one of a brightness evaluation result, a signal quality evaluation result, and a motion evaluation result.

3. The image output method according to claim 2, wherein: The adjusting the parameters of the camera based on the quality assessment result includes: Based on the brightness evaluation result being less than a brightness threshold, adjusting brightness-related parameters of the camera, wherein the brightness-related parameters include at least one of sensitivity, exposure, and white balance; Based on the signal quality evaluation result being less than a signal quality threshold, adjusting a signal quality-related parameter of the camera, wherein the signal quality-related parameter comprises at least one of zoom, resolution, and frame rate; Based on the motion evaluation result being less than a motion threshold, the motion-related parameters of the camera are adjusted, wherein the motion-related parameters include at least one of shutter speed, sensitivity, exposure and white balance, zoom, resolution and frame rate.

4. The image output method according to claim 3, wherein: The adjusting of the brightness-related parameters of the camera includes: increasing at least one of the sensitivity, exposure and white balance of the camera by a predetermined amount or to a next level, The adjusting the brightness-related parameters of the camera includes: increasing at least one of the zoom, resolution and frame rate of the camera by a predetermined amount or to a next level, The adjusting the motion-related parameters of the camera includes: increasing the shutter speed of the camera by a predetermined amount or increasing it to a next level.

5. The image output method according to claim 1, further comprising: Based on the number of times the adjustment is performed being equal to the adjustment number threshold or the parameter being adjusted to a maximum value, prompt information for improving the shooting environment or the shooting quality is output.

6. The image output method according to claim 1, wherein: The image quality decision model is trained by the following operations: Training the initial health measurement model using a standard environment data set to obtain parameters of the trained health measurement model, wherein the standard environment data set includes a first image of each training object among a plurality of training objects in a standard environment, real health data of the first image, environment parameters, and camera parameters; updating parameters of the initial image quality decision model based on the parameters of the trained health measurement model; The parameter-updated initial image quality decision model is trained using a real environment dataset, and the trained image quality decision model is used as the final image quality decision model, wherein the real environment dataset includes a second image of each training object among multiple training objects in multiple different real environments, real quality score data of the second image, environmental parameters, and camera parameters.

7. The image output method according to claim 6, wherein: The initial health measurement model is trained using a standard environment dataset, including: Inputting the standard environment data set into the initial health measurement model to obtain health measurement data output by the initial health measurement model; Calculating a difference between the health measurement data and the true health data as a first training loss; Parameters of the initial health measurement model are adjusted according to the first training loss.

8. The image output method according to claim 6, wherein: The method of using the real environment data set to train the initial image quality decision model with updated parameters includes: Inputting the real environment data set into the parameter-updated initial image quality decision model to obtain image quality score data output by the parameter-updated initial image quality decision model; Calculating a difference between the image quality score data and the true image quality score data as a second training loss; The parameters of the initial health measurement model are adjusted according to the second training loss.

9. A method for acquiring a user's biological health characteristics, comprising: Acquire a user image, wherein the user image is an output image obtained using the image output method according to any one of claims 1 to 6; A user biometric health characteristic is determined based on the user image.

10. An image output device, comprising: a quality assessment unit configured to determine a quality assessment result of an image acquired by a camera through an image quality decision model trained for biological health features; an output image determining unit, configured to determine the image as an output image in response to the quality assessment result satisfying a condition; a loop execution unit, configured to, in response to the quality evaluation result not satisfying the condition, adjust the parameters of the camera at least once based on the quality evaluation result, and determine, after each adjustment, a quality evaluation result of an adjusted image acquired by the adjusted camera through an image quality decision model, The output image determination unit is further configured to determine the adjusted image as the output image in response to the quality assessment result of the adjusted image satisfying the condition.

11. The image output device according to claim 10, wherein: The quality evaluation result includes at least one of a brightness evaluation result, a signal quality evaluation result, and a motion evaluation result.

12. The image output device according to claim 11, wherein: The loop execution unit is configured as follows: Based on the brightness evaluation result being less than a brightness threshold, adjusting brightness-related parameters of the camera, wherein the brightness-related parameters include at least one of sensitivity, exposure, and white balance; Based on the signal quality evaluation result being less than a signal quality threshold, adjusting a signal quality-related parameter of the camera, wherein the signal quality-related parameter comprises at least one of zoom, resolution, and frame rate; Based on the motion evaluation result being less than a motion threshold, a motion-related parameter of the camera is adjusted, wherein the motion-related parameter includes a shutter speed.

13. The image output device according to claim 10, wherein: The loop execution unit is configured to increase at least one of the sensitivity, exposure and white balance of the camera by a predetermined amount or to a next level, The loop execution unit is configured to increase at least one of the zoom, resolution and frame rate of the camera by a predetermined amount or to a next level, The loop execution unit is configured to increase the shutter speed of the camera by a predetermined amount or to a next level.

14. The image output device according to claim 10, further comprising: The prompt output unit is configured to output prompt information for improving the shooting environment or shooting quality based on the number of times the adjustment is performed being equal to the adjustment number threshold or the parameter being adjusted to a maximum value.

15. The image output device according to claim 10, wherein: The image quality decision model is trained by the following operations: Training the initial health measurement model using a standard environment data set to obtain parameters of the trained health measurement model, wherein the standard environment data set includes a first image of each training object among a plurality of training objects in a standard environment, real health data of the first image, environment parameters, and camera parameters; updating parameters of the initial image quality decision model based on the parameters of the trained health measurement model; The parameter-updated initial image quality decision model is trained using a real environment dataset, and the trained image quality decision model is used as the final image quality decision model, wherein the real environment dataset includes a second image of each training object among multiple training objects in multiple different real environments, real quality score data of the second image, environmental parameters, and camera parameters.

16. The image output device according to claim 15, wherein: The initial health measurement model is trained using a standard environment dataset, including: Inputting the standard environment data set into the initial health measurement model to obtain health measurement data output by the initial health measurement model; Calculating a difference between the health measurement data and the true health data as a first training loss; Parameters of the initial health measurement model are adjusted according to the first training loss.

17. The image output device according to claim 15, wherein: The method of using the real environment data set to train the initial image quality decision model with updated parameters includes: Inputting the real environment data set into the parameter-updated initial image quality decision model to obtain image quality score data output by the parameter-updated initial image quality decision model; Calculating a difference between the image quality score data and the true image quality score data as a second training loss; The parameters of the initial health measurement model are adjusted according to the second training loss.

18. A device for acquiring a user's biological health characteristics, comprising: an image acquisition unit, configured to acquire a user image, wherein the user image is an output image obtained using the image output method according to any one of claims 1 to 7; The health feature determination unit is configured to determine a user's biological health feature based on the user image.

19. A computer-readable storage medium storing a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

20. A computing device comprising: at least one processor; At least one memory stores a computer program, and when the computer program is executed by the at least one processor, the method according to any one of claims 1 to 9 is implemented.

Images