Abstract: A method for identifying skin region in an image includes: selecting a pixel in the target image; calculating a first probability of the pixel in a first color space, the first probability being a probability that the pixel represents skin in the first color space; calculating a second probability of the pixel in a second color space distinct from the first color space, the second probability being a probability that the pixel represents skin in the second color space; determining a combined probability that the pixel in the target image represents skin based on the first probability and the second probability; expanding the pixel into a skin region in the target image by repeating said steps of determining a combined probability that another pixel adjacent to the pixel represents skin until the skin region reaches a predefined size threshold; and performing a predefined beautifying process to the pixels.

Abstract: Embodiments include apparatus for predicting cancer recurrence based on local co-occurrence of cell morphology (LoCoM). The apparatus includes image acquisition circuitry that identifies and segments at least one cellular nucleus represented in an image of a region of tissue demonstrating cancerous pathology; local nuclei graph (LNG) circuitry that constructs an LNG based on the at least one cellular nucleus, and computes a set of nuclear morphology features for a nucleus represented in the LNG; LoCoM circuitry that constructs a co-occurrence matrix based on the nuclear morphology features, computes a set of LoCoM features for the co-occurrence matrix, and computes a LoCoM signature for the image based on the set of LoCoM features; progression circuitry that generates a probability that the region of tissue will experience cancer progression based on the LoCoM signature, and classifies the region of tissue as a progressor or non-progressor based on the probability.

Abstract: A system and method for training a computer-implemented object classifier includes detecting a foreground visual object within a sub-region of a scene, determining a background model of the sub-region of the scene, the background model representing the sub-region when any foreground visual object is absent from that sub-region, and training the object classifier by computer-implemented machine learning using the background model of the sub-region as a negative training example.

Abstract: Embodiments disclosed herein provide methods and systems for delineating cell nuclei and classifying regions of histopathology or microanatomy while remaining invariant to batch effects. These systems and methods can include providing a plurality of reference images of histology sections. A first set of basis functions can then be determined from the reference images. Then, the histopathology or microanatomy of the histology sections can be classified by reference to the first set of basis functions, or reference to human engineered features. A second set of basis functions can then be calculated for delineating cell nuclei from the reference images and delineating the nuclear regions of the histology sections based on the second set of basis functions.

Abstract: A finger vein identification method and device used for effectively extracting finger vein identification characteristics to conduct finger vein identification. The method of the embodiments of the present teachings comprises: collecting a finger vein image, employing a line fitting method to extract a region of interest in the finger vein image, conducting geometric normalization and grayscale normalization processing of the region of interest to obtain a processed region, determining finger vein blood vessel lines in the processed region to obtain a finger vein blood vessel image, and conducting finger vein identification based on the finger vein blood vessel image.

Abstract: An apparatus and method of denoising a dynamic image is provided. The dynamic image can represent a time-series of snapshot images. The dynamic image is transformed, using a sparsifying transformation, into an aggregate image and a series of transform-domain images. The transform-domain images represent kinetic information of the dynamic images (i.e., differences between the snapshots), and the aggregate image represents static information (i.e., features and structure common among the snapshots). The transform-domain images, which can be approximated using a sparse approximation method, are denoised. The denoised transform-domain images are recombined with the aggregate image using an inverse sparsifying transformation to generate a denoised dynamic image. The transform-domain images can be denoised using at least one of a principal component analysis method and a K-SVD method.

Abstract: The present invention provides a portable electronic device, including: a touch panel; a display module, disposed below the touch panel; an optical fingerprint sensor module, disposed below the display module; a transparent frame, disposed between the display module and the optical fingerprint sensor module, and including: a first surface, for combining with the display module; a second surface, for combining with the optical fingerprint sensor module; and an opening, running through the first surface and the second surface, and a filler type ultraviolet (UV) curable optically clear adhesive (OCA) being filled into the opening; and a housing, for combining with the touch panel.

Abstract: An analysis device includes an acquisition unit configured to acquire an image of a cell and an identification unit configured to identify elements that are identifiable on the basis of the image of cell acquired by the acquisition unit. Characteristic quantities of the elements identified by the identification unit are calculated, a correlation between the characteristic quantities is calculated on the basis of the calculated characteristic quantities of the elements, and a correlation between the elements is calculated on the basis of the calculated correlation between the characteristic quantities.

Abstract: An image processing method is provided, including: obtaining image data of a cavity wall of an organ; unfolding the cavity wall; and generating an image of the unfolded cavity wall. The unfolding of the cavity wall may include: obtaining a mask and a centerline of the organ; obtaining a connected region of the mask; dividing the connected region into at least one equidistant block; determining an orientation of the equidistant block in a three-dimensional coordinate system including a first direction, a second direction and a third direction; determining an initial normal vector and an initial tangent vector of a center point of the centerline; assigning a projection of the initial normal vector to a normal vector of a light direction of the center point; assigning the third direction or an reverse direction of the third direction to a tangent vector of the light direction of the center point.

Abstract: A Dynamic Vision Sensor (DVS) pose-estimation system includes a DVS, a transformation estimator, an inertial measurement unit (IMU) and a camera-pose estimator based on sensor fusion. The DVS detects DVS events and shapes frames based on a number of accumulated DVS events. The transformation estimator estimates a 3D transformation of the DVS camera based on an estimated depth and matches confidence-level values within a camera-projection model such that at least one of a plurality of DVS events detected during a first frame corresponds to a DVS event detected during a second subsequent frame. The IMU detects inertial movements of the DVS with respect to world coordinates between the first and second frames. The camera-pose estimator combines information from a change in a pose of the camera-projection model between the first frame and the second frame based on the estimated transformation and the detected inertial movements of the DVS.

Abstract: This disclosure generally pertains to methods and systems for processing electronic data obtained from imaging or other diagnostic and evaluative medical procedures. Certain embodiments relate to methods for the development of deep learning algorithms that perform machine recognition of specific features and conditions in imaging and other medical data. Another embodiment provides systems configured to detect and localize medical abnormalities on medical imaging scans by a deep learning algorithm.

Abstract: A first face region within a first image is determined. The first face region includes a location of a face within the first image. Based on the determined first face region within the first image, a predicted face region within a second image is determined. A first region of similarity within the predicted face region is determined. The first region of similarity has at least a predetermined degree of similarity to the first face region within the first image. Whether a second face region is present within the second image is determined. The location of the face within the second image is determined based on the first region of similarity, the determination of whether the second face region is present within the second image, and a face region selection rule.

Abstract: A Bayer-mask is decoded by forming a decoded green array, calculating red green and blue-green color difference signals, deriving a first full-resolution grid of each colour difference signal using a first interpolation filter; deriving a second full-resolution grid of each colour difference signal using a second interpolation filter taking a larger number of colour difference signal inputs than the first; generating a cross-colour weighting signal; and forming a mixed colour difference signal from the first and second full-resolution grids in accordance with the cross-colour weighting signal.

Abstract: Methods and systems for automatic video summary generation are disclosed. A method includes: extracting, by a computing device, a plurality of frames from a video; determining, by the computing device, for each of the plurality of extracted frames, features in the frame; creating, by the computing device, a scene detection model using the determined features for each of the plurality of extracted frames; scoring, by the computing device, each of the plurality of extracted frames using the created scene detection model; and generating, by the computing device, a video summary using the scored plurality of extracted frames.

Abstract: Methods and systems for high-speed filtering of candidate fingerprint images in a gallery using a non-reference-point based matching involving histograms of tokens representing minutia data. The method or system may involve detecting minutia patterns in a probe image, defining tokens that represent the minutia patterns detected in the probe image, measuring a degree of similarity between the probe image and each gallery image by comparing a probability of occurrence of a set of the tokens defined for the probe image with a probability of occurrence of the same set of tokens in that gallery image, and identifying as a candidate for a match to the probe image each gallery image for which the measured degree of similarity satisfies a criterion.

Abstract: A vehicle prompt apparatus and a corresponding method are provided. The method includes: acquiring an image recorded in real time by a designated terminal during driving; analyzing brightness distribution of the image and obtaining an analysis result; and when the analysis result is a first analysis result, communicating a warning message in accordance with a first prompting procedure, where the first analysis result indicates a vehicle light in the image. When other vehicles are present around the driving vehicle where the vehicle prompt apparatus is located, the acquired image may catch other vehicles' lights. By analyzing the brightness distribution in the image, when the analysis result indicates the presence of the vehicle lights, the driver can be prompted with the coming vehicle to improve the driving safety.

Abstract: A method for part mobility prediction based on a static snapshot consisting of several steps: constructing mobility units from each 3D model in a set of 3D models with parts segmented according to their motion and grouping all of the mobility units according to their motion type; computing snapshot descriptors for every static snapshot in a mobility unit; learning a snapshot-to-unit distance measure for every motion types of the mobility units; getting the most similar mobility unit and its motion type for a query static snapshot by using the snapshot-to-unit distance measure to select with the minimum distance value; generating multiple motion candidates for a query static snapshot according to the achieved mobility unit and its motion type, sampling the generated motion and getting the best motion parameter for the query static snapshot. This invention can predict the part mobility from a static snapshot of an object.

Abstract: A method and system for inspecting a customized orthodontic aligner for manufacturing defects are described. The method includes obtaining images of the customized orthodontic aligner, determining a digital file associated with the aligner, the digital file including a digital model of a mold used during manufacture of the customized orthodontic aligner, determining an inspection recipe for the aligner, determining an intended property for the customized orthodontic aligner by digitally manipulating the digital model of the mold, determining an actual property of the customized orthodontic aligner from the images, determining whether there is a manufacturing defect in the customized orthodontic aligner by comparing the intended property with the actual property, and outputting an output associated with the determination of whether there is a manufacturing defect.

Abstract: An image recognition apparatus (100) includes: an object specifying unit (102) that specifies a position, in a captured image, of a detection target object which is set in a predetermined arrangement according to a processing target object in an imaging target and has a feature depending on the processing target object, by image recognition; and a processing unit (104) that specifies, based on object position data indicating a relative position between the detection target object in the imaging target and the processing target object which is set in a predetermined arrangement according to the imaging target and has a feature depending on the imaging target, the processing target object in the captured image which is present at the relative position from the position, in the captured image, of the detection target object specified by the object specifying unit (102), and executes a process allocated to the specified processing target object.

Abstract: Systems and methods for correlating visual content in 2D and 3D scenes of a geographical region can include at least one data source for providing geographical data, a display device of an aircraft, and a processor. The display device can display a 2D view and a 3D view representing top-down views of the geographical region using data received from the data source(s). The processor(s) can identify a first image point within the 2D view referenced by a first cursor of the 2D view. The processor(s) can determine, using information received from the at least one data source, a geographical location corresponding to the first image point. The processor(s) can determine a second image point within the 3D view corresponding to the determined geographical location. The processor(s) can position a second visual indicator of the 3D view to reference the determined second image point within the 3D view.