Abstract: A magnetic resonance imaging apparatus according to embodiments includes processing circuitry. The processing circuitry configured to acquire layout information which defines a layout of cross-sectional images on a localizer screen, to detect cross-sectional positions of the cross-sectional images from MR data, and to generate the localizer screen according to the layout information, the localizer screen including all or a part of the plurality of cross-sectional images generated on the basis of the plurality of cross-sectional positions.

Abstract: Disclosed herein is method and system for detecting pose of a subject in real-time. In an embodiment, nodal points corresponding to the subject may be identified and used for identifying skeleton pose of the subject. Thereafter, a feature descriptor for the skeleton pose may be computed based on the nodal points. Further, the feature descriptor of the skeleton pose may be compared with predetermined feature descriptors for detecting the pose of the subject as predefined pose corresponding to one of the predetermined feature descriptors used for the comparison. The method of present disclosure makes accurate pose detection from a two-dimensional image of the subject, using a pose detection model, which is pre-trained with predetermined feature descriptors and deep learning techniques.

Abstract: Examples of the present disclosure relate to methods for processing image data. In one such example, data elements are received defining a portion of a line of pixels of an image, the image comprising one or more lines of pixels definable by one or more respective sets of data elements. In some cases, a transform operation is performed on the data elements to obtain a plurality of binary transform coefficients, wherein the transform operation is performed independently of data elements defining any other line of pixels. The plurality of transform coefficients is encoded as a sequence of tiered bit-layers, each bit-layer in the sequence of bit-layers comprising a set of bits corresponding to a given bit position in each of the plurality of transform coefficients. The encoded plurality of transform coefficients is output.

Abstract: Disclosed herein are computer-implemented methods, computer-implemented systems, and non-transitory, computer-readable media for evaluating performance of an object detection model. One computer-implemented method includes generating a predicted bounding box representing an object based on the object detection model, where the object is positioned proximate to one or more adjacent objects. An area of intersection is determined between the predicted bounding box and a groundtruth bounding box of the object. A modified area of union is determined between the predicted bounding box and the groundtruth bounding box of the object. A score equal to the area of intersection between the predicted bounding box and the groundtruth bounding box of the object divided by the modified area of union is determined, where the score represents the performance of the object detection model.

Abstract: There is provided a method for training a deep convolutional neural network (CNN) for detecting an indication of likelihood of abnormality, comprising: receiving anatomical training images, each including an associated annotation indicative of abnormality for the whole image without an indication of location of the abnormality, executing, for each anatomical training image: decomposing the anatomical training image into patches, computing a feature representation of each patch, computing for each patch, according to the feature representation of the patch, a probability that the patch includes an indication of abnormality, setting a probability indicative of likelihood of abnormality in the anatomical image according to the maximal probability value computed for one patch, and training a deep CNN for detecting an indication of likelihood of abnormality in a target anatomical image according to the patches of the anatomical training images, the one patch, and the probability set for each respective anatomical

Abstract: The apparatus for removing haze from an image using a fuzzy membership function includes memory configured to store computer-readable instructions; and a processor configured to execute the instructions, wherein the processor calculates a hazy value and a transmission map using an input image including a hazy component and generates a restored image from which the hazy component has been removed using the hazy value and the transmission map, and wherein the processor selects a first area in the input image, calculates a fuzzy membership function of pixels of the input image with respect to the hazy value using brightness values of the pixels of the input image and brightness values of pixels of the first area, and calculates the transmission map using the brightness values of pixels of the first area and the fuzzy membership function.

Abstract: An image processing apparatus includes: a filter unit configured to execute a filter process on each block area in the input image and output the filter processing result of each pixel in the input image; a supply unit configured to read out attribute information from the attribute map and supply attribute information for each pixel; and an image processing unit configured to perform the predetermined image processing for the filter processing result output by the filter unit based on the attribute information for each pixel supplied by the supply unit, wherein the pixel order in which the pixel value in the input image is received by the filter processing unit and the pixel order in which the filter processing unit outputs the filter processing result are different, and wherein the supply unit supplies the attribute information for each pixel according to the pixel order of the filter processing result.

Abstract: Certain embodiments involve using an image completion neural network to perform user-guided image completion. For example, an image editing application accesses an input image having a completion region to be replaced with new image content. The image editing application also receives a guidance input that is applied to a portion of a completion region. The image editing application provides the input image and the guidance input to an image completion neural network that is trained to perform image-completion operations using guidance input. The image editing application produces a modified image by replacing the completion region of the input image with the new image content generated with the image completion network. The image editing application outputs the modified image having the new image content.

Abstract: A mobile terminal includes a memory, and a processor coupled to the memory, wherein the processor executes a process comprising acquiring a frame with taking a photograph, acquiring document image data of a document from the frame, detecting shine on the document image data, determining whether the shine is equal to or smaller than a shine baseline, and acquiring a frame with retaking a photograph when the shine is neither equal to nor smaller than the shine baseline.

Abstract: A multi-label heat map generating system is operable to receive a plurality of medical scans and a corresponding plurality of global labels that each correspond to one of a set of abnormality classes. A computer vision model is generated by training on the medical scans and the global labels. Probability matrix data, which includes a set of image patch probability values that each indicate a probability that a corresponding one of the set of abnormality classes is present in each of a set of image patches, is generated by performing an inference function that utilizes the computer vision model on a new medical scan. Heat map visualization data can be generated for transmission to a client device based on the probability matrix data that indicates, for each of the set of abnormality classes, a color value for each pixel of the new medical scan.

Abstract: Provided are an image processing device, an image processing system, an image processing method, and an imaging optical system group capable of suppressing an increase in costs and appropriately restoring an image. In the imaging optical system, in a case where a first MTF curve M1 indicating an MTF value in a first azimuth direction with respect to an amount of defocus from a focal position is compared with a second MTF curve M2 indicating an MTF value in a second azimuth direction with respect to the amount of defocus from the focal position, a ratio of a peak value P1 of the first MTF curve M1 to a peak value P2 of the second MTF curve M2 is equal to or greater than 2, and a ratio of a half-value width HW2 of the second MTF curve M2 to a half-value width HW1 of the first MTF curve M1 is equal to or greater than 1.25. The restoration filter is a common filter corresponding to a representative value of transfer functions in a plurality of same type imaging optical systems.

Abstract: An image processing apparatus includes: a distance histogram information generating means configured to generate distance histogram information representing a frequency distribution of distance values in each of a plurality of row regions obtained by division of a captured image in an up-down direction; and a movement surface information processing means configured to: extract a group of distance values matching a feature represented by distance values of the movement surface for each of a plurality of segments obtained by segmentation of the distance histogram information according to the distance values; execute, for a segment where a group of distance values extracted does not satisfy a predetermined error condition, processing of generating information on the movement surface using the group of distance values; and execute, for a segment where a group of distance values extracted satisfies the predetermined error condition, predetermined error processing without using the group of distance values.

Abstract: Methods and apparatus for characterizing a subterranean formation traversed by a wellbore including collecting data from the formation using a tool wherein the tool collects data to form an azimuthal image, characterizing a section of the formation comprising data and images acquired in a high angle wellbore section or horizontal wellbore section using a parametric model, and performing an inversion using apparent densities and volumetric photoelectric factor images to build a formation model wherein the inversion is tailored for high angle wellbore sections and/or horizontal wellbore sections.

Abstract: Disclosed is a panoramic image mapping method, wherein mapping regions and a non-mapping region are partitioned for an equirectangular panoramic image with a resolution of 2M×M, where only the partitioned mapping regions are mapped as square regions; the method comprises:, computing a vertical distance and a horizontal distance from a point on the square region to a center of the square region, a larger one of which being denoted as m; computing a distance n from the point to a zeroth (0th) point on a concentric square region; computing a longitude and a latitude corresponding to the point; computing a corresponding position (X, Y) in the equirectangular panoramic image to which the point is mapped; and then assigning a value to the point. The method may effectively reduce oversampling, thereby effectively reducing the number of pixels of the panoramic image and the code rate required for coding with little distortion.

Abstract: A method for receiving an image query from a user via a client device is provided. The method includes determining a user personalized data based on a prior user history, generating a synthetic image with a generative tool, based on the image query and the user personalized data, and evaluating a similarity between the synthetic image and a real image in an image database with a discriminative tool. The method also includes providing the synthetic image to the user for selection and storing a user response to the synthetic image in the prior user history. A system and a non-transitory, computer readable medium storing instructions to cause the system to perform the above method are also disclosed.

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.