Abstract: Image processing apparatus 110 for applying a mask to an object, comprising an input 120 for obtaining an image 122, a processor 130 for (i) detecting the object in the image, and (ii) applying the mask to the object in the image for obtaining an output image 60, and the processor being arranged for said applying the mask to the object by (j) establishing an object contour of the object, (jj) generating, based on the object contour, a mask being smaller than the object, and (jjj) positioning the mask over the object for masking a body of the object while keeping clear a border area of the object.

Abstract: Disclosed herein are optimized techniques for controlling the exposure time or illumination intensity of a depth sensor. Invalid-depth pixels are identified within a first depth map of an environment. For each invalid-depth pixel, a corresponding image pixel is identified in a depth image that was used to generate the first depth map. Multiple brightness intensities are identified from the depth image. Each brightness intensity is categorized as corresponding to either an overexposed or underexposed image pixel. An increased exposure time or illumination intensity or, alternatively, a decreased exposure time or illumination intensity is then used to capture another depth image of the environment. After a second depth map is generated based on the new depth image, portion(s) of the second depth map are selectively merged with the first depth map by replacing the invalid-depth pixels of the first depth map with corresponding valid-depth pixels of the second depth map.

Abstract: An imaging apparatus includes first and second imaging devices configured to capture first and second images of a scene, respectively. The first and second images include multiple first image blocks relative to a first coordinate system and multiple second image blocks relative to a second coordinate system, respectively. The apparatus further includes a processor configured to calibrate one or more first image blocks and one or more corresponding second image blocks using the first and second coordinate systems, convert each calibrated first image block to an intensity image and a first depth map, convert each calibrated second image block to a grayscale image, and generate a second depth map associated with the second image by enhancing a resolution of the first depth map for each calibrated first image block based on calculating a relationship between the intensity image and the grayscale image for each calibrated first and second image blocks.

Abstract: An inspection image is assumed to contain many abnormalities when a reference image and an inspection image are misaligned. It has been impossible to determine whether the abnormalities are attributed to the inspection image. An image inspecting apparatus includes: a print alignment portion that aligns a print position of a reference image with a print position of an inspection image; an abnormality detector that detects an abnormality in the inspection image based on a difference between the reference image and the inspection image after print positions are aligned; and a print alignment result evaluator that evaluates a print position alignment result from aligning a print position of the reference image with a print position of the inspection image including an abnormality detected based on dispersion of the difference included in an evaluation region around an edge calculated from a printout image included in the reference image.

Abstract: A computer aided diagnostic system and automated method to classify a kidney utilizes medical image data and clinical biomarkers in evaluation of kidney function pre- and post-transplantation. The system receives image data from a medical scan that includes image data of a kidney, then segments kidney image data from other image data of the medical scan. The kidney is then classified by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker.

Abstract: Various techniques are provided for reducing noise in captured image frames. In one example, a method includes determining row values for image frames comprising scene information and noise information. The method also includes performing first spectral transforms in a first domain on corresponding subsets of the row values to determine first spectral coefficients. The method also includes performing second spectral transforms in a second domain on corresponding subsets of the first spectral coefficients to determine second spectral coefficients. The method also includes selectively adjusting the second spectral coefficients. The method also includes determining row correction terms based on the adjusted second spectral coefficients to reduce the noise information of the image frames. Additional methods and systems are also provided.

Abstract: Disclosed herein are computer-implemented methods; computer-implemented systems; and non-transitory, computer-readable media, for quantifying text similarity. One computer-implemented method includes obtaining a plurality of shortest operation paths including one or more edit pairs for correcting an optical correction recognition (OCR) text string with an edit text string, where each of the one or more edit pairs denotes an operation performable to a character of the OCR text string during correction by the edit text string. A plurality of similarity scores is determined, each corresponding to one of the plurality of shortest operation paths and determined by summing historical similarity scores of the one or more edit pairs of each of the plurality of shortest operation paths. A minimum one of the plurality of similarity scores is selected to quantify text similarity between the OCR text string and the edit text string.

Abstract: Embodiments of the invention provide a laser system including a laser station including at least one laser, at least one processor, and at least one non-transitory computer-readable storage medium in data communication with the at least one processor. The at least one non-transitory computer-readable storage medium includes program instructions executable by the at least one processor, and enabling or operating an exchange of data between the at least one laser station and at least one remote network. The laser system includes at least one GUI display configured and arranged to display operating parameters or functions of the at least one laser and/or any of the data exchanged between the laser station and at least one remote network. The program instructions include instructions that direct the processor to update the at least one GUI display with a plurality of user-selectable graphics arranged around the periphery or circumference of a central display.

Abstract: Systems and methods for developing a disease detection model. One method includes training the model using an image study and an associated disease label mined from a radiology report. The image study including a sequence of a plurality of two-dimensional slices of a three-dimensional image volume, and the model including a convolutional neural network layer and a convolutional long short-term memory layer.

Abstract: Methods and systems are provided for managing identifying information for an entity. The identifying information of the entity embedded in or associated with a digital image is detected, wherein the identifying information is selected from the group consisting of: text information and image information corresponding to one or more features of an entity. The text information may be removed from the digital image. The image information may be replaced with one or more computer generated synthetic images, wherein the computer generated synthetic images are based on a natural appearance of the digital image. The synthetic content, which may be generated by a GAN, is based on a natural appearance of the image. The medical image may also contain PHI in text-based fields associated with private tags/fields, which are automatically identified and removed using the systems and methods provided herein.

Abstract: A target object recognition method includes: performing target object detection on an object of an image to be detected to obtain target object prediction information of the object, where the target object prediction information is confidence information that the detected object is the target object; performing key point detection on the object of the image to be detected to obtain key point prediction information of the object, where the key point prediction information is confidence information that a key point of the detected object is a key point of the target object; fusing the target object prediction information with the key point prediction information to obtain comprehensive prediction information of the object; and recognizing the target object according to the comprehensive prediction information.

Abstract: A liveness test method and apparatus is disclosed. The liveness test method includes detecting a face region in an input image for a test target, implementing a first liveness test to determine a first liveness value based on a first image corresponding to the detected face region, implementing a second liveness test to determine a second liveness value based on a second image corresponding to a partial face region of the detected face region, implementing a third liveness test to determine a third liveness value based on an entirety of the input image or a full region of the input image that includes the detected face region and a region beyond the detected face region, and determining a result of the liveness test based on the first liveness value, the second liveness value, and the third liveness value.

Abstract: The present invention relates to a method for registering a first anatomical structure (1) which is articulately coupled to a second anatomical structure (2), the method being constituted to be executed by a computer and comprising the steps of: acquiring second structure correlation data describing the spatial position of at least one correlation feature (3) relative to the second anatomical structure (2); acquiring coupling data describing a positional fixation (6) of the first anatomical structure (1) relative to the second anatomical structure (2), which is set by the articulated coupling (4) between the first anatomical structure (1) and the second anatomical structure (2); determining, based on the second structure correlation data and the coupling data, first structure correlation data describing the spatial position of the at least one correlation feature (3) relative to the first anatomical structure (1). The present invention further relates to a corresponding computer program and system.

Abstract: Methods and systems for visually focused first-person neural network interpretation are disclosed. A method includes: receiving, by a computing device, an image; determining, by the computing device, feature vectors from the image; determining, by the computing device, a first padding value and a first stride value by inputting the feature vectors into a deep neural network; determining, by the computing device, a second padding value and a second stride value by inputting the feature vectors into at least one multiple regression model; determining, by the computing device, padding by averaging the first padding value and the second padding value; determining, by the computing device, stride by averaging the first stride value and the second stride value; and classifying, by the computing device, the image using a convolutional neural network using the padding and the stride.

Abstract: An object detector includes an input interface to accept a sequence of video frames, a memory to store a neural network trained to detect objects in the video frames, a processor to process each video frame sequentially with the neural network to detect objects in the sequence of video frames, and an output interface to output the object detection information. The neural network includes a first subnetwork, a second subnetwork, and a third subnetwork. The first subnetwork receives as an input a video frame and outputs a feature map of the video frame. The second subnetwork is a recurrent neural network that takes the feature map as an input and outputs a temporal feature map. The third subnetwork takes the temporal feature map as an input and outputs object detection information.

Abstract: A method for the three-dimensional graphic or pictorial reconstruction of a vehicle begins with capturing an image of at least one vehicle with a camera. A first rectangular border of the entire vehicle is captured in the image, to obtain a first rectangle. A second rectangular border of one side of a vehicle is captured in the image, to obtain a second rectangle, and it is determined whether the first and second rectangles are borders which relate to the same vehicle. If so, then it is determined whether a side orientation of the vehicle can be assigned from the two rectangles and, if so, the side orientation is determined. Finally, a three-dimensional reconstruction of the vehicle is performed from the first rectangle, the second rectangle and the side orientation.

Abstract: An object characteristic locating device is provided, which includes a camera module and a processing module. The camera module is configured to capture an image from a front scene. The processing module is configured to perform the following operations: locating a position of an image object in the captured image, and determining a framing range with the image object from the captured image; and preforming image processing on the framing range according to a characteristic of the image object, so as to locate the position of an image characteristic portion of the image object in the captured image.

Abstract: Various techniques are provided for reducing noise in captured image frames. In one example, a method includes determining row values for image frames comprising scene information and noise information. The method also includes performing first spectral transforms in a first domain on corresponding subsets of the row values to determine first spectral coefficients. The method also includes performing second spectral transforms in a second domain on corresponding subsets of the first spectral coefficients to determine second spectral coefficients. The method also includes selectively adjusting the second spectral coefficients. The method also includes determining row correction terms based on the adjusted second spectral coefficients to reduce the noise information of the image frames. Additional methods and systems are also provided.

Abstract: Magnetic resonance imaging (MRI) systems and methods determine slice leakage and/or residual aliasing in the image domain in accelerated MRI imaging. Implementations process one slice of MRI image domain data by input to a sensitivity encoding (SENSE) un-aliasing matrix built from predetermined RF signal reception sensitivity maps, thereby producing as matrix output SENSE-decoded MRI image domain data for one pass through image slice and at least one extra slice, and determine inter-slice leakage and/or in-plane residual aliasing based on content of the at least one extra output slice from the SENSE-decoded MRI image domain data.

Abstract: Present embodiments pertain to systems, apparatuses, and methods for analyzing and reporting the movements in mechanical structures, inanimate physical structures, machinery, and machine components, including automatically detecting aliased frequencies of a component on the structure which exhibits frequencies higher than the maximum frequency of the FFT spectrum calculated from the acquired data. To automatically detect the presence of aliased frequencies, a second virtually identical recording is acquired using a slightly different sampling rate and this provides the basis for detecting frequencies which are greater than the Nyquist sampling rate of the video recording and calculating the true frequency value of the aliased peaks in the frequency spectrum.