Abstract: A method of adaptive image enhancement, comprising, receiving a low resolution image, receiving at least one application constraint, detecting at least one scene within the low resolution image, detecting a plurality of regions of interest within the detected at least one scene, prioritizing the detected plurality of regions of interest, ranking the detected plurality of regions of interest based on the prioritization, determining an enhanceable subset of the plurality of regions of interest based on the ranking of the plurality of regions of interest and the at least one application constraint and enhancing the enhanceable subset of the plurality of regions of interest.

Abstract: The present disclosure discloses a convolutional neural network processor, an image processing method and an electronic device. The method includes: receiving, by the first convolutional unit, the input image to be processed, extracting the N feature maps with different scales in the image to be processed, sending the N feature maps to the second convolutional unit, and sending the first feature map to the processing unit; fusing, by the processing unit, the received preset noise information and the first feature map, to obtain the second feature map, and sending the second feature map to the second convolutional unit; and fusing, by the second convolutional unit, the received N feature maps with the second feature map to obtain the processed image.

Abstract: A device and a method for electromagnetic field simulation are provided. The image processing device is to obtain, with a first resolution, a first electromagnetic field simulation result of a simulation region, and to derive a second electromagnetic field simulation result with a second resolution, according to the first electromagnetic field simulation result, using a model trained based on a deep learning method. The second resolution is higher than the first resolution.

Abstract: Systems, methods, and non-transitory computer readable media can align face images, classify face images, and verify face images by employing a deep neural network (DNN). A 3D-aligned face image can be generated from a 2D face image. An identity of the 2D face image can be classified based on provision of the 3D-aligned face image to the DNN. The identity of the 2D face image can comprise a feature vector.

Abstract: An artificial intelligence (AI) encoding apparatus includes a processor configured to execute one or more instructions stored in the AI encoding apparatus to: input, to a downscale deep neural network (DNN), a first reduced image downscaled from an original image and a reduction feature map having a resolution lower than a resolution of the original image; obtain a first image AI-downscaled from the original image in the downscale DNN; generate image data by performing a first encoding process on the first image; and output the image data.

Abstract: Briefly, embodiments disclosed herein relate to image cropping, such as for digital images, for example.

Abstract: Methods and systems are described herein for improvements to authenticate users, particularly authenticating a user based on data known to the user. For example, methods and systems allow for users to be securely authenticated based on data known to the users over remote communication networks without storing the data known to the users. Specifically, methods and systems authenticate users by requiring users to select images that are known to the users. For example, the methods and systems may generate synthetic images based on the user's own images and require the user to select the synthetic image, from a set of a set of images, that is known to the user to authenticate the user. Moreover, the methods and systems alleviate storage and privacy concerns by not storing the data known to the users.

Abstract: A system and method of generating a player tracking prediction are described herein. A computing system retrieves a broadcast video feed for a sporting event. The computing system segments the broadcast video feed into a unified view. The computing system generates a plurality of data sets based on the plurality of trackable frames. The computing system calibrates a camera associated with each trackable frame based on the body pose information. The computing system generates a plurality of sets of short tracklets based on the plurality of trackable frames and the body pose information. The computing system connects each set of short tracklets by generating a motion field vector for each player in the plurality of trackable frames. The computing system predicts a future motion of a player based on the player's motion field vector using a neural network.

Abstract: A method, computer program product, and customized image processing system provide aided target recognition (AiTR) using manifold transfer substance learning (MTSL). The method includes receiving image data. The method includes performing manifold learning technique comprising diffusion mapping on the received image data to transform the received image data. The method includes applying a transfer subspace learning technique comprising Transfer Fishers Linear Discriminative Analysis (TrFLDA) to the transformed data to recognize an object within the image data.

Abstract: Provided are an image processing device, an image processing method, a program, and a recording medium which are capable of classifying a plurality of persons appearing in an image set into groups. In an image processing device, an image processing method, a program, and a recording medium according to an embodiment of the present invention, a plurality of persons appearing in an image set is determined. In a case where two or more persons among the plurality of persons appear in the image based on a determination result of the plurality of persons for each image included in the image set, co-occurrence relation information indicating that the two or more persons have a co-occurrence relation in the image is stored. A co-occurrence score indicating strength of the co-occurrence relation of two persons in the image set is calculated based on all the co-occurrence relation information items in the image for each permutation of the two persons of the plurality of persons.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing action localization in images and videos. In one aspect, a system comprises a data processing apparatus; a memory in data communication with the data processing apparatus and storing instructions that cause the data processing apparatus to perform image processing and video processing operations comprising: receiving an input comprising an image depicting a person; identifying a plurality of context positions from the image; determining respective feature representations of each of the context positions; providing a feature representation of the person and the feature representations of each of the context positions to a context neural network to obtain relational features, wherein the relational features represent relationships between the person and the context positions; and determining an action performed by the person using the feature representation of the person and the relational features.

Abstract: A method includes capturing a first image via a camera of an electronic device using a first set of image capture parameters. The method includes identifying a first object in the first image based on an object recognition model. The method includes sending first image data to a server. The first image data includes first information associated with the first object. The method includes capturing a second image via the camera using a second set of image capture parameters. The method includes identifying a second object in the second image based on the object recognition model. The method includes sending second image data to the server. The second image data includes second information associated with the second object. The method also includes receiving location information from the server. The location information is determined by the server based on the first information and the second information.

Abstract: An artificial intelligence (AI) decoding method including obtaining image data generated from performing first encoding on a first image and AI data related to AI down-scaling of at least one original image related to the first image; obtaining a second image corresponding to the first image by performing first decoding on the image data; obtaining, based on the AI data, deep neural network (DNN) setting information for performing AI up-scaling of the second image; and generating a third image by performing the AI up-scaling on the second image via an up-scaling DNN operating according to the obtained DNN setting information. The DNN setting information is DNN information updated for performing the AI up-scaling of at least one second image via joint training of the up-scaling DNN and a down-scaling DNN used for the AI down-scaling.

Abstract: Techniques for training an optical character recognition (OCR) model to detect and recognize text in images for robotic process automation (RPA) are disclosed. A text detection model and a text recognition model may be trained separately and then combined to produce the OCR model. Synthetic data and a smaller amount of real, human-labeled data may be used for training to increase the speed and accuracy with which the OCR text detection model and the text recognition model can be trained. After the OCR model has been trained, a workflow may be generated that includes an activity calling the OCR model, and a robot implementing the workflow may be generated and deployed.

Abstract: Methods for annotating objects within image frames are disclosed. Information is obtained that represents a camera pose relative to a scene. The camera pose includes a position and a location of the camera relative to the scene. Data is obtained that represents multiple images, including a first image and a plurality of other images, being captured from different angles by the camera relative to the scene. A 3D pose of the object of interest is identified with respect to the camera pose in at least the first image. A 3D bounding region for the object of interest in the first image is defined, which indicates a volume that includes the object of interest. A location and orientation of the object of interest is determined in the other images based on the defined 3D bounding region of the object of interest and the camera pose in the other images.

Abstract: A method for analyzing a polymer membrane, which can improve accuracy of structural analysis of the polymer membrane and shorten the analysis time by effectively removing noise is provided.

Abstract: A computer vision system and method for detecting and modeling features of a building in a plurality of images is provided. The system includes at least one computer system in communication with a database of aerial imagery, and computer vision system code executed by the at last one computer system which automatically detects contours and infers interior roof features of the building. The system first processes the plurality of images to identify a plurality of two-dimensional (2D) line segments in each image. Then, the system processes the plurality of 2D line segments to generate a plurality of three-dimensional (3D) line segments. The plurality of 2D line segments are then processed to detect a contour of the structure, and the contour of the structure is utilized by the system to infer interior roof lines from the structure. A model of the roof of the structure is finally generated using the detected contour and interior roof lines.

Abstract: A method for detecting a posture, including: acquiring an image to be detected; and inputting the image to be detected into a pre-trained detection model, and detecting a posture category in the image to be detected. The detection model is acquired by training based on a positive sample image and a negative sample image, a basic posture categorization model is acquired by training based on the positive sample image with a marked preset posture category, and the negative sample image is determined based on the basic posture categorization model, and the negative sample image contains no posture of the preset posture category and the positive sample image is an image inputted by an user or an image stored at a preset storage location.

Abstract: A method and system for image processing of an image captured by an image-capturing device, can involve dividing a region of interest in an image into blocks, wherein the image is captured by an image-capturing device. The region of interest can be associated with one or more faces in the image, and a resulting division of the dividing of the region of interest may be non-uniform. A minimum block size can be defined and the coordinates of each block after dividing of the region of interest in the image into the blocks. The one or more faces in the image can be redacted and reconstructed using the coordinates. In addition, redacting and reconstructing of the image is reversible for use with detecting the one or more faces in the image. The coordinates can specify top left coordinates and bottom right coordinates of each block.

Abstract: Systems and methods acquire and/or generate multiple different images of the same biometric identity, identify specific instances of biometric features in each of the different images, and merge the identified specific instances of biometric features into a data record that provides a digital representation of the biometric identity. Examples of biometric identities include fingerprints, handprints, palm prints, and thumbprints. In one embodiment, a counter is associated with each specific instance of a biometric feature found in the multiple images. Specific instances of biometric features found most frequently have high counts and are indicative of true identifications; those with low counts are indicative of false identifications. A threshold distinguishes between true and false identifications. Those specific instances with counts below the threshold are excluded when the digital representation of the biometric identity is generated.