Abstract: Disclosed is a control method for an infrared light source assembly (10). The method is used for an electronic device (100), wherein the electronic device (100) comprises a camera (20). The infrared light source assembly (10) comprises at least two infrared light sources (12) having different illumination ranges. The control method comprises: (S32) controlling the camera (20) so that same collects a face image; (S34) processing the face image to acquire face position information; and (S36) starting, according to the face position information, an infrared light source (12) having an illumination range corresponding to that into which a face falls, and turning off other infrared light sources (12) or keeping some turned off. Further disclosed are an electronic device (100) and a computer-readable storage medium (800).

Abstract: Alignment precision technology, in which a system accesses image data of a bone to which a reference marker array is fixed. The system generates a three-dimensional representation of the bone and the reference markers, defines a coordinate system for the three-dimensional representation, and determines locations of the reference markers relative to the coordinate system. The system accesses intra-operative image data that includes the bone and a mobile marker array that is attached to an instrument used in a surgical procedure. The system co-registers the intra-operative image data with the three-dimensional representation by matching the reference markers included in the intra-operative image data to the locations of the reference markers. The system determines locations of the mobile markers in the co-registered image and determines a three-dimensional spatial position and orientation of the instrument relative to the bone.

Abstract: A method of training a neural network for home improvement visualization is disclosed. The method may include receiving a set of annotated images of houses to train the neural network, augmenting the set of annotated images of houses to generate additional annotated images of houses for the neural network, processing the annotates images of houses and the additional annotated images of houses to train the neural network, refining the set of annotated images of houses by detecting the edges elements in the images and adjusting the annotations based on the edge detection, and outputting a trained neural network.

Abstract: The disclosure features dendritic tags, and methods and systems for fabricating and using such tags. The methods can include obtaining at least one image of a dendritic tag attached to an article, analyzing the at least one image to identify a set of features associated with the dendritic tag, and comparing the set of features to stored information to identify the article.

Abstract: Disclosed is an eyeball movement analysis system. The eyeball movement analysis system includes an image capturing unit configured to acquire a first image of an eyeball at a reference location and acquire a second image of the eyeball at a moved location, and an eyeball movement analyzing unit configured to calculate a rotational angle of the eyeball and a translational distance of the eyeball in a process of moving the eyeball from the reference location to the moved location through comparison of the first image and the second image.

Abstract: Systems and methods are provided for feature detection such that users can apply advanced machine learning and artificial intelligence (AI) without the need for a deep understanding of existing algorithms and techniques. Embodiments of the present disclosure provide systems and methods than enable easy access to a suite of machine learning algorithms and techniques, an intuitive interface for training an AI to recognize image features based on geometric “correct and refine” recursion, and real-time visualizations of training effectiveness.

Abstract: Provided are a method and a device for determining an iris recognition image, a terminal apparatus and a storage medium. The method includes: detecting a line of sight of a user; acquiring a user image based on the line of sight of the user; and if the user image meets a specified condition, determining the user image as the iris recognition image. With the method, the accuracy of iris recognition during iris recognition is improved, and the time for iris recognition is reduced.

Abstract: A citation system may receive data, including an image, from a handheld photo enforcement unit and issue a citation based on the image with minimal officer input. The citation system manipulates photos to identify license plate numbers involved in an event. The citation system requests identification from a driver database, issues a citation, and forwards the citation according to information from the driver database.

Abstract: The present invention provides a system for reading a license plate from a poor image captured in various environments. To this end, the present invention provides a license plate reading apparatus and method using deep learning technology and provides a license plate learning apparatus and method for generating and providing a restoration neural network and a recognition neural network by using the license plate reading apparatus and method, thereby implementing a circular recognition network generating and using system.

Abstract: An example method for segmenting an object contained in an image includes receiving an image including a plurality of pixels, transforming a plurality of characteristics of a pixel into respective neutrosophic set domains, calculating a neutrosophic similarity score for the pixel based on the respective neutrosophic set domains for the characteristics of the pixel, segmenting an object from background of the image using a region growing algorithm based on the neutrosophic similarity score for the pixel, and receiving a margin adjustment related to the object segmented from the background of the image.

Abstract: Various embodiments of the disclosure relate to devices and methods for user authentication on an electronic device. The electronic device comprises a plurality of lighting devices, a camera, a display, and a processor. The processor is configured to display an object on the display, obtain, through the camera, a plurality of images based on an image obtaining pattern randomly generated, obtain biometric information using at least one of the plurality of images, obtain information about a variation in a user's gaze corresponding to a movement of the object displayed on the display using the plurality of images, and perform authentication on the user based on the biometric information and the user gaze variation information. Other embodiments are available as well.

Abstract: A method for image capture includes identifying a bright spot in an image. A neural network is used to recover details in bright spot area through a trained de-noising process. Post-processing of the image is conducted to match image parameters of recovered details in the bright spot area to another area of the image.

Abstract: A text recognition method, a text recognition apparatus, an electronic device, and a storage medium are provided. The method includes: extracting character prediction regions of a text line image using a constructed text recognition model, to obtain a character region set; calculating horizon-distance IOUs between the character prediction regions in the character region set according to a position of each character prediction region in the character region set; removing overlapped character prediction regions from the character region set, according to the horizon-distance IOUs between the character prediction regions in the character region set, to obtain a character position set; and sorting and outputting character categories corresponding to the character prediction regions in the character position set according to positions of the character prediction regions in the character position set.

Abstract: The disclosure is directed at a method and apparatus for a flat panel X-ray imaging detector. In one embodiment, the apparatus includes three (3) layers including a top layer, an intermediate layer and a bottom layer. The top layer generates a top layer image; the intermediate layer generates an intermediate layer image; and the bottom layer generates a bottom layer image. The intermediate layer also operates simultaneously as an intermediate X-ray energy filter.

Abstract: A recording reproduction apparatus includes: a captured data acquisition unit configured to acquire first captured data captured by a first camera that captures an image of an outside of a moving body and second captured data captured by a second camera that captures an image in a direction opposed to a display surface of a display unit; an event detection unit configured to detect an event on the moving body; a recording controller configured to store, when an event has been detected, the first captured data as event recording data; a face detection unit configured to detect a human face from the second captured data; a reproduction controller configured to reproduce the event recording data when a human face has been detected within a period after storage of the event recording data; and a display controller configured to cause the display unit to display the reproduced event recording data.

Abstract: Safety systems in distributed factory workcells intercommunicate or communicate with a central controller so that when a person, robot or vehicle passes from one workcell or space into another on the same factory floor, the new workcell or space need not repeat the tasks of analysis and classification and can instead immediately integrate the new entrant into the existing workcell or space-monitoring schema. The workcell or space can also communicate attributes such as occlusions, unsafe areas, movement speed, and object trajectories, enabling rapid reaction by the monitoring system of the new workcell or space.

Abstract: An ocular imaging system comprising: an image acquisition module which acquires a retinal image; a landmark location prediction module which predicts locations of at least two landmarks in the retinal image; and an apparatus for alerting a user to an unreliability in at least one of the predicted locations. The apparatus receives the predicted first locations; uses the predicted locations to evaluate a distance metric indicative of a distance between the landmark features; use data indicative of a probability distribution of a distance between the landmark features obtained from measurements of the distance in retinal images different from the retinal image to determine an indication of whether the evaluated distance metric lies outside a predetermined interval about a peak the probability distribution; and generates an alert indicating the unreliability when the determined indication indicates that the evaluated distance metric lies outside the predetermined interval.

Abstract: An image processing method includes receiving an image source, and detecting whether the image source is a high dynamic range (HDR) image. If the image source is the HDR image, reading a first image adjustment value, and performing color adjustment to the image source according to the first image adjustment value.

Abstract: An image data is convolved with one or more kernels and corresponding one or more feature maps generated. Region of interest maps are extracted from the one or more feature maps, and pooled based on one or more features selected as selective features. Pooling generates a feature vector with dimensionality less than a dimensionality associated with the one or more feature maps. The feature vector is flattened and input as a layer in a neural network. The neural network outputs a classification associated with an object in the image data.

Abstract: A recording reproduction apparatus includes: a captured data acquisition unit configured to acquire first captured data captured by a first camera that captures an image of an outside of a moving body and second captured data captured by a second camera that captures an image in a direction opposed to a display surface of a display unit; an event detection unit configured to detect an event on the moving body; a recording controller configured to store, when an event has been detected, the first captured data as event recording data; a face detection unit configured to detect a human face from the second captured data; a reproduction controller configured to reproduce the event recording data when a human face has been detected within a period after storage of the event recording data; and a display controller configured to cause the display unit to display the reproduced event recording data.