Abstract: A method for assessing a condition of an organ or tissue of a target object is provided. The method may include: obtaining a target image of the target object; segmenting a target region from the target image, the target region of the target image corresponding to a sub-region of the organ or tissue; determining a morphological characteristic value of the target region in the target image; obtaining a reference standard associated with a sample organ or tissue of a plurality of sample objects, the sample organ or tissue being of a same type as the organ or tissue of the target object; and assessing the condition of the organ or tissue of the target object by comparing the morphological characteristic value of the target region in the target image with the reference standard.

Abstract: A system for gaze direction detection is disclosed herein. The system comprises a face detection unit configured to detect face information from a captured image of a spectator, a head pose unit configured to detect a head pose angle based on the face information; an eye measurement unit configured to detect eye information of at-least one of a left eye or a right eye of the spectator based on the detected face information; an eye-gaze detection unit configured to estimate a gaze angle of the at-least one of the left eye or the right eye of the subject based on the eye information; a conditional gaze detection unit configured to calculate a resultant gaze angle based on the estimated gaze angles of the left eye and right eye and the head pose angle; and an effective gaze detection unit configured to estimate an effective gaze angle based the resultant gaze angle and head-pose angle.

Abstract: A video display device includes: a video receiver that receives video data including a video and dynamic luminance characteristics indicating a time-dependent change in luminance characteristics of the video; a tone mapping processor that, in the case where a luminance region having a luminance less than or equal to a first luminance is defined as a low luminance region, and a luminance region having a luminance exceeding the first luminance is defined as a high luminance region, (i) performs first tone mapping using first conversion characteristics when first luminance characteristics exceed a predetermined threshold value, and (ii) performs second tone mapping using second conversion characteristics when the first luminance characteristics are less than or equal to the predetermined threshold value.

Abstract: A method is provided for simultaneously recognizing facial attributes and identity to organize photo and/or video albums, based on modifying an efficient convolutional neural network (CNN) which extracts facial representations suitable for face identification and attribute (age, gender, ethnicity, emotion, etc.) recognition tasks. The method enables to process all the tasks simultaneously, without a need for additional CNNs. As a result, a very fast facial analytic system is provided, and the system can be installed onto mobile devices.

Abstract: Embodiments described herein provide a system for assessing the surface of an object for detecting contamination or other defects. During operation, the system obtains an input image indicating the contamination on the object and generates a synthetic image using an artificial intelligence (AI) model based on the input image. The synthetic image can indicate the object without the contamination. The system then determines a difference between the input image and the synthetic image to identify an image area corresponding to the contamination. Subsequently, the system generates a contamination map of the contamination by highlighting the image area based on one or more image enhancement operations.

Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

Abstract: A terminal according to an embodiment is for tracking eyes on the basis of a first eye tracking model in which multiple pieces of learning data related to line-of-sight information are accumulated. The terminal may include a data collecting unit which obtains a facial image of a user using an imaging device, and extracts line-of-sight information about the user from the facial image, a data transmitting unit which transmits, to a server, the line-of-sight information about the user and location information about a point to which a line of sight of the user is directed within a screen of the terminal; a model receiving unit which receives from the server a second eye tracking model obtained by training the first eye tracking model with the line-of-sight information and the location information, and an eye tracking unit which tracks eyes of the user using the second eye tracking model.

Abstract: Systems and methods are disclosed for predicting healthy lumen radius and calculating a vessel lumen narrowing score. One method of identifying a lumen diameter of a patient's vasculature includes: receiving a data set including one or more lumen segmentations of known healthy vessel segments of a plurality of individuals; extracting one or more lumen features for each of the vessel segments; receiving a lumen segmentation of a patient's vasculature; determining a section of the patient's vasculature; and determining a healthy lumen diameter of the section of the patient's vasculature using the extracted one or more features for each of the known healthy vessel segments of the plurality of individuals.

Abstract: Machine learning based models recognize objects in images. Specific features of the object are extracted from the image using machine learning based models. The specific features extracted from the image assist deep learning based models in identifying subtypes of a type of object. The system recognizes the objects and collections of objects and determines whether the arrangement of objects violates any predetermined policies. For example, a policy may specify relative positions of different types of objects, height above ground at which certain types of objects are placed, or an expected number of certain types of objects in a collection.

Abstract: A high-dimensional image feature matching method and device relating to the field of image retrieval. The method includes extracting a high-dimensional image feature of an image to be retrieved; dividing the high-dimensional image feature of the image to be retrieved into a plurality of low-dimensional image features; comparing each of the low-dimensional image features of the image to be retrieved with clustering centers at each layer of the low-dimensional image features of the images in a database; and determining a similarity the low-dimensional image feature between the image to be retrieved and each of some images in the database according to a comparison result, so that at least one feature matching the high-dimensional image feature of the image to be retrieved is retrieved in the database.

Abstract: There is provided a biometric imaging system comprising: a display panel comprising: a plurality of display pixels controllable to form an image in the display and a plurality of individually controllable non-visible light emitting elements configured to the emit non-visible light, the non-visible light emitting elements being configured to form a controllable spatial irradiation pattern within an irradiation zone defined by the plurality of non-visible light emitting elements; and a control unit. The control unit is configured to identify a biometric object facing the display panel; determine a relative location of the biometric object in the irradiation zone; control the plurality of non-visible light emitting elements to form a spatial radiation pattern based on the location of the biometric object in relation to the display panel.

Abstract: A system and method for instant tongue sampling and diagnosis includes acquiring a plurality of tongue images from a plurality of digital oral devices, and a current health conditions, building a diagnosis framework for diagnosing a current health condition of a user by: i) analyzing the collected tongue images with a visual recognition engine to determine tongue characteristics of each tongue captured in the tongue images, and ii) correlating the tongue characteristics with the current health condition, identifying tongue characteristics from a received image of the tongue using the visual image recognition engine, applying the diagnosis framework to the tongue characteristics of the tongue to diagnosis the current health condition of the user, and modifying a graphical user interface of the digital oral device to display a custom health report indicative of the current health condition of the user, in response to applying the diagnosis framework.

Abstract: A spoofing detection apparatus comprises obtaining, from an image capture apparatus, a first image frame that includes the face of a subject person obtained when a light-emitting apparatus is emitting light and a second image frame that includes the face of the subject person obtained when the light-emitting apparatus is turned off, extracting, from the first image frame, information specifying a face portion of the subject person, and extract, from the second image frame, information specifying a face portion of the subject person, extracting a portion that includes a bright point formed by reflection in an iris region of an eye of the subject person, from the first image frame, extracts a portion corresponding to the portion that includes the bright point, from the second image frame, and calculates a feature that is independent of the position of the bright point, and determining authenticity of subject person based on the feature.

Abstract: A method of determining footprint identity using a dimension reduction algorithm according to an embodiment includes: pre-processing to process three-dimensional (3D) image data about footprints of a first person and a second person and convert the 3D image data into one-dimensional (1D) data about the footprints of the first person and the second person; calculating a distribution of cross-correlation coefficients between two pieces of 1D data about footprints of the first person (SC: same footwear correlation) and a distribution of cross-correlation coefficients between the 1D data about the footprints of the first person and the second person (DC: difference footwear correlation); and calculating a likelihood ratio based on the SC and the DC to determine the degree of correspondence between the footprints of the first person and the second person.

Abstract: In some aspects, the described systems and methods provide for a method for training a statistical model to predict tissue characteristics for a pathology image. The method includes accessing annotated pathology images. Each of the images includes an annotation describing a tissue characteristic category for a portion of the image. A set of training patches and a corresponding set of annotations are defined using an annotated pathology image. Each of the training patches in the set includes values obtained from a respective subset of pixels in the annotated pathology image and is associated with a corresponding patch annotation determined based on an annotation associated with the respective subset of pixels. The statistical model is trained based on the set of training patches and the corresponding set of patch annotations. The trained statistical model is stored on at least one storage device.

Abstract: A terminal, a server, and a system for authenticating biometric information and a biometric information authentication method are provided. A method, performed by a terminal, of registering biometric information includes: transmitting a registration request and biometric capability information of the terminal to a server; receiving biometric capability information of the server from the server; acquiring a user's biometric information based on the biometric capability information of the server; acquiring a pseudonymous identifier (PI) and auxiliary data (AD) based on the user's biometric information; and transmitting the PI and the AD to the server.

Abstract: The present principles relates to a method and device for tone-mapping an input picture by using a parametric tone-adjustment function. The method is characterized in that the method comprises determining at least one parameter of said tone-adjustment function modulated by a brightness level of the input picture.

Abstract: An apparatus configured to generate an output quality error estimate using a machine-learning error estimation model to compare an output meeting a predetermined quality threshold with an output image reconstructed from a plurality of images, and provide the output quality error estimate for use in estimating if a second subsequent image is required, in addition to a first subsequent image to obtain a cumulative output having an output quality error meeting a predetermined error threshold. Also an apparatus configured, using a received output quality error estimate generated using a machine-learning error estimation model as above, to estimate if a second subsequent image is required, in addition to a first subsequent image, to obtain a cumulative output having an output quality error meeting a predetermined error threshold.

Abstract: Systems, methods, and non-transitory computer-readable media can provide at least one frame of a content item to a saliency prediction model, the saliency prediction model being trained to identify salient points of interest that appear in content items. Information describing at least a first salient point of interest that appears in the at least one frame can be obtained from the saliency prediction model. The first salient point of interest can be predicted to be of interest to users accessing the content item. A view-based projection can be applied to a region corresponding to the first salient point of interest, wherein the view-based projection enhances a quality in which the region is presented.

Abstract: A method of plane tracking comprising: capturing by a camera a reference frame of a given plane from a first angle; capturing by the camera a destination frame of the given plane from a second angle different than the first angle; defining coordinates of matching points in the reference frame and the destination frame; calculating, using the first and second angles, first and second respective rotation transformations to a simulated plane parallel to the given plane; applying an affine transformation between the reference frame coordinate on the simulated plane and the destination frame coordinate on the simulated plane; and applying a projective transformation on the simulated plane destination frame coordinate to calculate the destination frame coordinate.