Abstract: Systems and methods for identifying fields in an electronic document using classification and scale invariant template matching. The method includes receiving an electronic document having fields and processing the electronic document into digital pages. The method also includes determining, for each of the digital pages, a corresponding document type. The method further includes identifying at least one of the digital pages containing a structured field based on the document type. The method also includes extracting a structured template from a database corresponding to the document type and identifying an optimal match between the structured field and the structured template using scale invariant template matching. The method further includes determining, in response to identifying the optimal match, coordinates corresponding to the structured field.

Abstract: A computer system displays an annotation placement user interface that includes a representation of a field of view of one or more cameras that is updated over time based on changes in the field of view, a placement user interface element indicating a virtual annotation placement location. If the placement user interface element is over a representation of a physical feature in the physical environment that can be measured, the appearance of the placement user interface element changes in accordance with one or more aspects of the representation of the physical feature, and, in response to an input to perform one or more measurements of the physical feature: if the physical feature is a first type of feature, measurements of a first measurement type are made; and, if a second, different type of physical feature, measurements of a second, different measurement type are made.

Abstract: Disclosed are a color reconstruction device and method capable of accurately recovering the missing color of a target pixel. The device includes: a direction-characteristic estimation circuit calculating a horizontal-variation characteristic and a vertical-variation characteristic according to a first color of a target pixel and the values of pixels within a reference range, in which the target pixel is in the reference range and a current value of the target pixel is a first color value; an edge-texture decision circuit determining which of N predetermined relations matches the relation between the horizontal-variation characteristic and the vertical-variation characteristic and thereby determining the directional characteristic of the target pixel, in which the N is not less than four; and a color recovery circuit calculating a second and a third color values of the target pixel according to the directional characteristic and the values of the pixels within the reference range.

Abstract: Provided herein are systems, methods and computer readable media for classification of documents using a location hierarchy.

Abstract: Various embodiments of the disclosure relate to systems and methods for aligning a sequence read to a graph reference. In one embodiment, the method comprises selecting a first node from a graph reference, the graph reference comprising a plurality of nodes connected by a plurality of directed edges, at least one node of the plurality of nodes having a nucleotide sequence. The method further comprises traversing the graph reference according to a depth-first search, and comparing a sequence read to nucleotide sequences generated from the traversal of the graph reference. The traversal of the graph is then modified in response to a determination that each and every node associated with a given nucleotide sequence was previously evaluated.

Abstract: Described is a system for real-time object recognition. The system extracts a candidate target region representing a candidate object from an input image of a scene based on agglomeration of channel features. The candidate target region is classified using a trained convolutional neural network (CNN) classifier, resulting in an initial classified object. A multi-target tracker is used for tracking the classified objects for final classification of each classified object, resulting in a final output, and a device is controlled based on the final output.

Abstract: An image data processing method includes receiving first frame image data at a first resolution, reducing a resolution of the first frame image data to a second resolution, performing image recognition on the first frame image data to determine one or more regions of interest (ROI) and a priority level of each of the ROIs; receiving second frame image data, and extracting portions of the second frame image data corresponding to the one or more ROIs. The method further includes modifying a resolution of the portions of the second frame image data corresponding to the ROIs based on the priority level of the ROIs, reducing a resolution of the received second frame image data to the second resolution, and combining the resolution-modified portions of the second frame image data corresponding to the ROIs with the second frame image data at the second resolution to generate output frame image data.

Abstract: Ultrasound B-mode images are reconstructed directly from transducer channel signals using a convolutional neural network (CNN). The CNN is trained with a dataset including, as inputs, simulated transducer array channel signals containing simulated speckle and, as outputs, corresponding simulated speckle-free B-mode ground truth images. After training, measured real-time RF signals taken directly from an ultrasound transducer array elements prior to summation are input to the CNN and processed by the CNN to generate as output an estimated real-time B-mode image with reduced speckle.

Abstract: Deep learning of dental images for national security is described. A computer may receive dental images of a patient from a dental provider. The computer is configured to match dental images to law enforcement databases such as a terrorist database. The process begins with matching a dental image to an anatomy probability dataset and a pathology probability dataset, then correlating it with a patient database to identify a person of interest. With different resolutions each neural network deep learns to probability map and detect different dental object probabilities to authenticate an individual. Further, the dental images will be associated with GPS coordinates to track movements of an individual. The datasets will be provided to e-commerce providers, e-commerce consumers, e-commerce administrators, machine learning entities, government entities and law enforcement entities which may exchange or transfer the data over a communication network such as the internet to locate a person of interest.

Abstract: An electronic apparatus including an adjustment determination unit structured to receive patient interface device information for a patient interface device including one or more adjustable features and a 3-D model of a patient's face, and to calculate adjustment information for the patient interface device corresponding to the patient's face using the patient interface device information and the 3-D model of the patient's face and an output unit structured to output the adjustment information.

Abstract: A method of reading a coupon channel that displays a test section pattern after being exposed to a target substance, the method uses a device having a computer readable memory, digital camera, logic assembly and user interface; providing a pixel target intensity profile; placing the coupon in the device and exposing the coupon channel to a test fluid mixture; automatically using the digital camera to take a digital image of the coupon channel test section after the exposure. The improvement in the method includes finding the contiguous set of pixels from the test section of the coupon channel that best matches the intensity profile of the target pattern representation and determining if this best match set of pixels exceeds a similarity threshold and in response to a best match set of pixels passing the similarity threshold, automatically providing a human perceptible indication that the target substance has been detected.

Abstract: A method for scattered radiation correction acquires radiographic projection image data for a first portion of a subject that lies within a field of view of an imaging apparatus and characterizes the surface contour of the subject that includes at least a second portion of the subject that lies outside the field of view of the imaging apparatus. The surface contour of the subject is characterized according to the reflectance images. The surface contour characterization is registered to the field of view. Scattered radiation is estimated according to the projection image data and the surface contour characterization. The acquired radiographic projection image data is updated according to the estimated scattered radiation. An image of the field of view is displayed according to the conditioned acquired radiographic projection image data.

Abstract: In an embodiment, a method includes providing a three-dimensional structure image including surface data relating to external contours and structure data relating to internal structures of a body region; recording the body region via a camera system, to produce a recording while a patient is situated in or on the medical imaging system; registering, at least locally and as a structure image, the three-dimensional surface image in relation to the three-dimensional structure image; producing an overlay image including at least part of the structure image registered including structure data of the three-dimensional structure image in a form of an overlay with at least one of the three-dimensional surface image and a real view of a corresponding part of the body region of the patient; and controlling the medical imaging system to record body regions of the patient based upon an arrangement of the structure data registered in the overlay image.

Abstract: An apparatus for controlling a vehicle includes a sensor that detects motion and approach of an object around the vehicle, a camera that obtains a motion image and a facial image of the object around the vehicle, and a controller that generates a graphical user interface (GUI) based on the obtained motion and facial images of the object around the vehicle.

Abstract: Disclosed is an image processing apparatus that includes one or more processors; and a memory, the memory storing instructions. When executed by the one or more processors, cause the one or more processors to: generate distribution data indicating a frequency distribution of horizontal distance values of a range image based on the range image having pixel values according to distance of an object in a plurality of captured images; predict a predicted position of the object in the distribution data with respect to a range image of a current frame, based on the distribution data with respect to range images of a plurality of previous frames; and continue tracking of the object, based on a similarity between a region of the object in a previous frame and a region in the current frame with respect to the predicted position of the object.

Abstract: The invention relates to an apparatus and a system for visualizing an image object relating to an instrument (3), particularly a medical instrument, in an extracorporeal image. The image object may comprise a representation of the instrument (3) or an intracorporeal image (40) acquired using the instrument (3). The system comprises an extracorporeal image acquisition device (1) for acquiring extracorporeal images with respect to an extracorporeal image frame and a tracking arrangement (2) for tracking the instrument (3) independent of the extracorporeal images with respect to a tracking frame. Further, the invention relates to a method carried out in the system.

Abstract: An image processing method, an apparatus and a device are provided. The method includes: a first image is captured according to a preset first exposure time and a second image is captured according to a second exposure time by using dual cameras; a first foreground area and a first background area of the first image are determined, and a second foreground area of the second image is determined; image fusion is performed on the second foreground area and the first foreground area to generate a third foreground area; and blurring processing is performed on the first background area, and the third foreground area and the first background area subjected to the blurring processing are composed to generate a target image.

Abstract: Described is a system for visual activity recognition that includes one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations including detecting a set of objects of interest in video data and determining an object classification for each object in the set of objects of interest, the set including at least one object of interest. The one or more processors further perform operations including forming a corresponding activity track for each object in the set of objects of interest by tracking each object across frames. The one or more processors further perform operations including, for each object of interest and using a feature extractor, determining a corresponding feature in the video data. The system may provide a report to a user's cell phone or central monitoring facility.

Abstract: According to one embodiment, a medical image diagnostic apparatus includes processing circuitry. The processing circuitry configured to generate initial restored signal data by applying a first restoration function to input signal data corresponding to medical signal data concerning an object, generate first element-wise product signal data by calculating an element-wise product of the initial restored signal data and reliability data representing a degree of degradation included in the input signal data, and generate restored signal data by applying a second restoration function to at least one of the input signal data and the initial restored signal data and the first element-wise product signal data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a biometric authentication system. In one aspect, a method includes broadcasting, through a transceiver, a signal that includes a kiosk identifier; receiving, from a server system, a reference image of the user based on a mobile computing device associated with the user having received the signal and providing the kiosk identifier to the server system; capturing, with a camera, an image of the user; and authenticating the user based on a comparison of the captured image of the user to the reference image of the user based on a comparison of the captured image of the user to the reference image of the user.