152 results about "Image selection" patented technology

A multi-selection shutter camera application and method selectively sends images to different artificial intelligence and innovative platforms for fast sharing and informational purposes. An electronic device with a touch sensitive display and a processor is utilized. A capture screen on the display includes a multi-shutter view (a live view and at least two selective capture buttons (e.g., shutters)) for capturing media content. The method may include receiving input from the buttons to capture the content and direct it to an artificial intelligence platform; processing the content information based on the selected button; analyzing the content through parameters and show options to the user on the same screen that displays the content; and presenting a plurality of selectable options related to the user's selected shutter and intent of capturing the content, including, but not limited to uses related to at least one of the following: discovery, shopping and sharing functionality alternatives.

The invention discloses a radar anti-interference method based on frequency domain modeling and image collaboration, and the method comprises the steps: S10, carrying out the preprocessing of an original echo, and finally packaging a preprocessing result into a three-order tensor form; s20, performing FNO interference feature extraction and identification, and outputting interference type probability distribution and an interference-to-signal ratio estimation value through a de-wharf; s30, selectively processing the image, and reconstructing the histogram into an SAR image in an equalization manner; s40, evaluating the credibility of the image, and outputting an imaging credibility score between 0 and 1 through a regression head; s50, generating a credibility-interference combined criterion for judging the reliability of the radar guidance state; s60, a loss function is designed, back propagation is carried out through a total loss function, the model gradient is updated, and model parameters are optimized; and S70, dynamic anti-interference strategy matching: retrieving candidate anti-interference actions from a preset strategy library based on the interference types, performing grading and sorting according to complexity, and when the joint risk score is lower than a set threshold value, activating the optimal high-complexity anti-interference process of the corresponding interference type.

A media application receives an initial image, user input that selects one or more objects in the initial image, and a textual request to generate an output image that modifies the one or more selected objects in the initial image. The media application generates a user-selected mask that includes object pixels corresponding to the one or more selected objects. A diffusion model receives the textual request to generate the output image, a depth map, and the user-selected mask, where the diffusion model is trained to generate output pixels that are not associated with a human subject. The diffusion model outputs the output image that satisfies the textual request.

The invention relates to the technical field of visual inspection of photovoltaic modules, in particular to a line scanning solar module image self-adaptive splicing method based on a battery piece grid structure. The method comprises the following steps: synchronizing sub-images of the solar module and corresponding cell grid parameters, and extracting key points of each sub-image based on the cell grid parameters; determining a splicing mode of the sub-images, and calculating a position posture of each sub-image based on the key points and the splicing mode; determining the placement position of each sub-image based on the position attitude; selecting different splicing effective areas for each sub-image, and generating a standard splicing image and an extended splicing image based on the placement positions and the splicing effective areas; mapping the cell grid parameters to a standard spliced image and an extended spliced image to obtain a complete spliced image; according to the invention, the adaptive splicing of the solar module image is realized, the splicing precision of the image is improved, and the splicing precision is ensured to meet the technical requirements of photovoltaic module defect detection.

A method for in-situ scan band localization includes generating an in-situ scan band localization database by selecting a plurality of high contrast alignment targets from a set of pixel-to-design alignment images within a pixel-to-design alignment database. The method includes executing a first runtime scan band of a plurality of runtime dies, wherein each runtime frame associated with the first runtime scan band includes a high contrast alignment target from the in-situ scan band localization database. The method may include determining one or more offset values for each runtime die based on the plurality of high contrast alignment targets and one or more runtime frames associated with the first runtime scan band. The one or more offset values may include an x offset value and a y offset value for each die. The method may include adjusting an initial stage position based on the determined one or more offset values prior to executing a second runtime scan band.

Global index values for selecting global reshaping functions for an input image are generated using luminance codewords in the input image that have a relatively low dynamic range. Image filtering is applied to the input image to generate a filtered image. Filtered values of the filtered image provide a measure of local brightness levels in the input image. Local index values for selecting particular local reshaping functions for the input image are generated using the global index values and the filtered values of the filtered image. A reshaped image of a relatively high dynamic range is generated by reshaping the input image with the particular local reshaping functions selected using the local index values.

The invention discloses a digital material selection method and material selection equipment for an AIGC home design scene, relates to the technical field of artificial intelligence, and is used for improving the accuracy of selecting a physical entity material according to an AIGC image. In the method, a material selection device identifies and quantifies a non-physical rendering style fingerprint of an AIGC image, and rejects the non-physical rendering style fingerprint from a feature level to obtain an intrinsic texture topology tensor representing a texture structure; and aligning the intrinsic texture topology tensor to a feature space of a real physical building material through a preset domain generalization feature mapping network, thereby forcibly ignoring the interference of an AIGC rendering style in a retrieval process, focusing on the comparison of the texture topology structure, and further improving the accuracy of selecting a physical entity material according to the AIGC image.

An object of the system according to the embodiment is to enable a programming beginner to obtain an idea of an appropriate product and concentrate on learning.SOLUTION: A system according to an embodiment includes a skill selection unit, an image selection unit, a deliverable generation unit, and a learning material provision unit. The skill selection unit selects a programming skill of the user. The image selection unit selects an image of a product that the user wants to create. The deliverable generation unit generates an idea of the deliverable based on the information selected by the skill selection unit and the image selection unit. The learning material providing unit provides learning materials based on the information selected by the skill selection unit and the image selection unit.SELECTED DRAWING: Figure 1

The invention provides an image processing method and device, electronic equipment and a storage medium, and the method is applied to the image processing device, and comprises the steps: obtaining a target image and N primary color concentration sets corresponding to the target image; generating N preview images corresponding to the N primary color concentration sets according to the target image and the N primary color concentration sets; displaying the N preview images; determining a target preview image in response to a preview image selection operation triggered by a user; and adjusting a primary color concentration parameter of the image forming device according to the primary color concentration set corresponding to the target preview image. A user can see the presentation effect of the target image on the image forming medium before the image forming device executes the image forming operation, and after the image forming device completes the image forming operation and generates the output image, the output image is almost the same as the preview image, so that the image forming efficiency is improved. At the moment, the color of the actual output image is the same as the color of the preview image seen by the user, and the user experience is improved.

The present application is applicable to the technical field of data processing, and provides an image processing method and apparatus, a terminal device, and a storage medium. The method comprises: in response to a first operation, determining at least one first image from a gallery; displaying a thumbnail of the at least one first image in an image selection interface; and in response to a second operation, obtaining at least one second image on the basis of a target image among the at least one first image. In the embodiments of the present application, when a user opens an image selection interface of an application having an AI image processing function, images in a gallery can be screened so as to determine a first image that can be used for new AI image processing, reducing the number of displayed images, thereby reducing the difficulty for users in selecting images, and improving the operation efficiency of users.

The present disclosure relates to a method for synchronous navigation and annotation of a set of interrelated heterogeneous medical images.SOLUTION: The method includes correlating the first and second sets of sequential tomographic medical images of the subject based on the first metadata and the second metadata to generate a plurality of correlated image pairs, superimposing each correlated image pair to generate a fused image corresponding to the correlated image pair, selectively and sequentially rendering the correlated image pair, the fused image, and / or a third tomographic medical image of the subject, and selectively rendering a visual indication of a pixel of interest and / or a region of interest for the correlated image pair, the fused image, and / or the third tomographic medical image. A machine learning algorithm is used to identify pixels in the medical image that are associated with the medical condition. A graphical annotation is rendered at or near the location of the pixel.SELECTED DRAWING: Figure 3

The image processing device 1X includes a classification means 31X, an image selection means 33X, and a region extraction means 34X. The classification means 31X classifies each captured image acquired in time series by photographing an inspection target by a photographing unit provided in an endoscope, according to whether or not the each captured image includes an attention part to be paid attention to. The image selection means 33X selects a target image to be subjected to extraction of a region of the attention part from the each captured image, based on a result of the classification. The region extraction means 34X extracts the area of the attention part from the target image. The image processing device can support decision-making based on based on images captured by the endoscope.

In one aspect, the method includes causing presentation of a camera interface, the camera interface to display a first image captured by a camera of a computing device of a first user, causing presentation of a plurality of augmentation icons within the camera interface, each of the image augmentation icons being associated with a respective image augmentation mechanism, detecting user selection of an auxiliary augmentation icon of the plurality of image augmentation icons, the second image icon being associated with an second image augmentation mechanism, determining an second image selection criterion for an second image augmentation mechanism, selecting an second image based on the second image selection criterion, the second image being selected from a plurality of photographs associated with the first user, and overlaying the second image on the first image to generate a composite image that is presented within the camera interface.

The disclosure provides a series of photo selection method and system based on multi-view aesthetics, relates to the field of aesthetic quality evaluation, and the method comprises the following steps: acquiring image data; performing multi-view feature extraction on the image data, extracting artificial features and deep features of the series of images, obtaining node relationships between the extracted multi-views, constructing a multi-view aesthetic graph structure based on the node relationships; inputting the constructed multi-view aesthetic graph structure into a graph convolutional neural network, performing graph convolution, and refining feature maps through message passing between nodes; introducing an adaptive weight attention mechanism to compress and excite the input multi-view features, obtain the correlation between the multi-view features and highlight the common features; migrating each feature parameter obtained above to a twin network, inputting a series of images into the twin network, passing through three fully connected layers, obtaining the comparison result of the images, and obtaining the final series of image selection results.

Various methods and systems are provided for cervix elastographic analysis. In one embodiment, the method comprises acquiring an ultrasound scene comprising a plurality of frames, generating a first loss image for the plurality of frames, selecting a background and a foreground of the ultrasound scene based on the first loss image, and generating a softness ratio from the selected background and foreground.

The application discloses a kind of deep neural network test picture selection method and system based on multi-objective optimization, to improve the accuracy of image recognition system.The application first collects the picture test data in different application scenarios as the original picture test set of pre-training image recognition model.Then according to the size of picture test set, design picture test subset selection individual, and design the uncertainty and diversity of two indexes of picture test subset, use multi-objective optimization algorithm NSGA-II to solve the problem, finally obtain the Pareto optimal solution set.Finally, according to the Pareto optimal solution set, the optimal picture test subset is obtained, and the pre-trained image recognition model is retrained to improve the accuracy of the model.The application introduces the uncertainty and diversity of two indexes of picture test subset, so that the model can learn more diversified features during retraining, thereby achieving better retraining effect and improving the quality of image recognition system to the greatest extent.

The invention relates to a session-based interaction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to a background image selection operation that a first user selects a target image as a background image of a session in which the first user participates, displaying a session interface preview taking the target image as the background image, and in response to completion of background image setting, displaying a session interface of the session facing the first user, and displaying the target image as a background image of the session interface, displaying a background image setting result of the background image of the set session interface in the session interface, and displaying a background image sharing result of notifying a second user in the session of the background image setting result. By adopting the method, resources can be saved.

A method for curating a machine learning training library of calcareous nannofossil images for automated biostratigraphic analysis. The method includes receiving a plurality of images of various source materials from a target geologic time period. A subset of images is selected, comprising images from both a hydrocarbon-rich region and a hydrocarbon-poor region. A training library is generated based on this subset, enabling the development of machine learning models capable of accurate fossil identification and classification across diverse geological settings.

An image-for-training selecting apparatus for suitably selecting an image-for-training for training a machine learning model includes at least one processor executing: a first training process of training, by contrastive learning using an images-for-training set, a first machine learning model including a first layer group; a second training process of training a second machine learning model including the first layer group and a second layer group and employing the first machine learning model as a pre-trained model; a first calculating process of calculating a first similarity between a parameter of the first layer group after training by the first training process but before training by the second training process and a parameter of the first layer group after training by the second training process; and a first determining process of determining, based on the first similarity, whether the images-for-training set includes an inappropriate image-for-training.

A method is disclosed. The method includes receiving, by a server computer, a plurality of images associated with one or more service providers. The server computer then receives an inquiry request, and determines an image of the plurality of images. The image is selected in response to a composite score based on a scoring algorithm scoring each image in the plurality of images. The scoring algorithm comprises a conversion component and an uncertainty component. The server computer provides an inquiry response comprising the image to the end user device operated by the end user.

The invention provides a road image selection method and device for an edge node, equipment and a medium, and the method comprises the steps: segmenting and deploying a target image to a target edge node, obtaining a target image segmentation model through quantification processing, and obtaining multiple frames of to-be-selected road images; segmenting and identifying multiple frames of to-be-selected road images through the target image segmentation model to obtain a target entity in each frame of to-be-selected road image, performing range frame selection on the target entities to obtain a key entity region, and calculating the confidence of the key entity region to obtain a target entity region; a target entity area in each frame of to-be-selected road image is obtained through screening according to the confidence coefficient, the image similarity of the target entity areas in the adjacent frames of to-be-selected road images is calculated, and a target road image is selected from the multiple frames of to-be-selected road images according to the image similarity; the road image selection method for the edge nodes is more efficient and more accurate.

A media application receives an initial image, user input that selects one or more objects in the initial image, and a textual request to generate an output image that modifies the one or more selected objects in the initial image. The media application generates a user-selected mask that includes object pixels corresponding to the one or more selected objects. A diffusion model receives the textual request to generate the output image, a depth map, and the user-selected mask, where the diffusion model is trained to generate output pixels that are not associated with a human subject. The diffusion model outputs the output image that satisfies the textual request.

Disclosed are systems and methods for selecting images using motion data. Video data and motion metadata can be received from a camera. A frame in the video data can be selected using the motion metadata. An image can be generated using the selected frame. A user interface comprising an element based on the image can be generated.

The invention discloses a training method and a detection method of an infrared small target detection model, and belongs to the technical field of target detection. In a training process, a potential false alarm risk of a target domain image is predicted through a false alarm prediction model every preset iteration times, and entropy information of the target domain image is calculated based on a probability mask graph of the target domain image so as to measure the uncertainty that a target area in the target domain image is captured by a detection model; active sampling scores of the target domain images are calculated by synthesizing the false alarm risk and the entropy information, and K target domain images with the maximum active sampling scores are taken out for labeling and then are put into a current source domain image set; according to the method, a potential false alarm risk is brought into a scoring mechanism of target domain image selection, and meanwhile, based on an entropy sampling strategy of global gray level distribution, the difference between a target and a background can be accurately reflected, the loss of target information is avoided, and the accuracy of infrared small target detection is improved with relatively low labeling cost.

In response to detecting a triggering event corresponding to placement of a first item on a platform, a plurality of images are captured of the first item and a plurality of cropped images are generated based on the first images. An item identifier is identified based on each cropped image, wherein each item identifier is associated with a numerical similarity value. Each cropped image is further tagged as a front image or a back image. A particular item identifier identified for a corresponding cropped image tagged as a front image is selected and associated with the first item. An indicator of the particular item identifier is displayed on a user interface device.

The objective of the present invention is to provide a technique enabling efficient improvement of inference accuracy in a system for detecting an object by using a teacher AI model and an on-site AI model.　To this end, a learning image selection / analysis system according to the present invention comprises: an on-site analysis server that selects a learning image from input images acquired by an image acquisition unit; and an annotation / AI model learning server that annotates the learning image and trains an object detection AI model. The learning image selection / analysis system is characterized in that a plurality of on-site analysis servers are installed, and one on-site analysis server includes: an object detection unit that performs object detection using the on-site AI model; a detection difficulty calculation unit that calculates a detection difficulty of the teacher AI model and the on-site AI model with respect to the input image; and a learning image selection unit that automatically selects a learning image for each object detection AI model by using an output result of the detection difficulty calculation unit.

The present disclosure relates to the technical field of computer vision, in particular to a data processing method and device, electronic equipment and computer program product, which randomly selects a first image and a second image from an original semantic segmentation dataset; randomly transforms the first image and the second image respectively to obtain a third image and a fourth image; selects a first recognition object and a pixel label of the first recognition object from the third image; pastes the first recognition object and the pixel label of the first recognition object to a random position of the third image to obtain a target image, which can enhance the semantic segmentation dataset and effectively improve the diversity of the original dataset.

A measuring device includes a light source that irradiates a measurement spot on a wafer formed with memory holes and slits with a multi-wavelength light, a first imaging unit that acquires a first pupil plane intensity distribution image of reflected light from the measurement spot, a second imaging unit that acquires a second pupil plane intensity distribution image of the reflected light, and a detection unit that analyzes the second pupil plane intensity distribution image to measure overlay. The measuring device includes an overlay analysis unit that acquires the first and second pupil plane intensity distribution images while moving a position of the measurement spot and selects a measurement spot not including the slit based on the first pupil plane intensity distribution image, and uses the overlay obtained by analyzing the second pupil plane intensity distribution image of the selected measurement spot as the overlay of the memory hole and a slit.