Abstract: A method and apparatus to scan and measure the surface of objects using a radiation source, such as a laser. When combined with bio-data from bio-sensors to create a profile, the invention is particularly useful for measuring the internal surface of a prosthetic socket and improving the fit between the socket and the residual limb.

Abstract: A method for magnetic resonance imaging performs unsupervised training of a deep neural network of an MRI apparatus using a training set of under-sampled MRI scans, where each scan comprises slices of under-sampled, unclassified k-space MRI measurements. The MRI apparatus performs an under-sampled scan to produce under-sampled k-space data, updates the deep neural network with the under-sampled scan, and processes the under-sampled k-space data by the updated deep neural network of the MRI apparatus to reconstruct a final MRI image.

Abstract: A system including: at least one processor; and at least one memory having stored thereon instructions that, when executed by the at least one processor, control the at least one processor to: receive image data of a sequence of images, and a current image of the sequence of images being after a previous image in the sequence of images, each of the current and previous images including a cell; filter the current image to remove noise; iteratively deconvolve the filtered current image to identify edges of the cell within the current image based on determined edges of the cell within the previous image; and segment the deconvolved current image to determine edges of the cell within the current image.

Abstract: Systems, methods and software are provided that include a cloud, internet, and/or browser, application, or server based medical image sharing method and system that shares at least one 2D image data file through an internet browser that can generate rotatable and manipulatable 3D and/or 4D images by additional users without additional computer software, plug-ins, or hardware, to render 3D and 4D medical images for remote collaborative analysis, discussion, and/or diagnoses and that simulate or facilitate imaging of medical procedures for purposes of optimized performance, simulation, training and/or accreditation; as well as generating 3D and/or 4D imaging from 2 or more 2D images and/or projections for such use as semi-automated and/or fully automated, network and/or web-based, 3D and/or 4D imaging.

Abstract: Sketch and style based image retrieval in a digital medium environment is described. Initially, a user sketches an object to be searched in connection with an image search. Styled images are selected to indicate a desired style of images to be returned by the search. A search request is generated based on the sketch and selected images. Responsive to the request, an image repository is searched to identify images having the desired object and styling. To search the image repository, a neural network is utilized that is capable of recognizing the desired object in images based on visual characteristics of the sketch and independently recognizing the desired styling in images based on visual characteristics of the selected images. This independent recognition allows desired styling to be specified by selecting images having the style but not the desired object. Images having the desired object and styling are returned.

Abstract: A method of reconstructing an image of a colon, including receiving scan data of a colon taken by an imaging capsule that traverses the colon; wherein the imaging capsule emits X-ray radiation inside the colon and includes detectors that detect photons that are returned toward the imaging capsule from X-ray fluorescence and Compton back scattering interactions responsive to the radiation; and wherein the scan data includes counts of photons detected by each detector from X-ray fluorescence and Compton back scattering interactions; defining an initial guess of a geometry of a contour of a slice of the colon; calculating count values for each detector responsive to the geometry using a forward model; comparing the calculated count values of each detector with the values from the scan data; if the results of the comparison do not indicate reaching an optimal match then adjust the defined geometry and repeat the calculating and comparing.

Abstract: A face replacement system for replacing a target face with a source face can include a facial landmark determination model having a cascade multichannel convolutional neural network (CMC-CNN) to process both the target and the source face. A face warping module is able to warp the source face using determined facial landmarks that match the determined facial landmarks of the target face, and a face selection module is able to select a facial region of interest in the source face. An image blending module is used to blend the target face with the selected source region of interest.

Abstract: The invention relates to an optical biometric imaging device configured to capture an image of an object in contact with an outer surface of the biometric imaging device, the biometric imaging device comprising: an image sensor comprising a photodetector pixel array; a transparent substrate arranged to cover the image sensor; a transmission mask arranged to cover the transparent substrate, wherein the transmission mask comprises a plurality of openings, the openings forming a coded aperture configured to project a coded image of an object in contact with the outer surface of the imaging device onto the image sensor; and image sensor circuitry configured to capture an image corresponding to the coded image projected onto the image sensor.

Abstract: Methods and systems are described for autonomous control of imaging devices. In particular, the methods and system described herein may account for the differences in normalization of training data and/or test data. The methods and systems may process images through an additional customization layer, which itself may comprise an artificial neural network. The additional customization layer is trained to normalize data for specific applications and/or differences between subsets of data.

Abstract: A method of qualifying physical components using computed tomography (CT) includes obtaining qualified CT data from a CT scanner for at least one qualified physical component. Qualification data is generated based on the qualified CT data, where the qualification data defines a qualification envelope. Candidate CT data is obtained from the CT scanner for a candidate physical component. Comparison data is then generated based on the candidate CT data and the qualification data, where the comparison data indicates whether the candidate CT data is within the qualification envelope defined by the qualification data. An acceptance signal is generated if the comparison data meets acceptance criteria.

Abstract: Embodiments of this specification disclose systems and methods for automotive part recognition based on a vehicle damage assessment image. A method includes: obtaining a damage assessment image of a target vehicle; obtaining an automotive part list of the target vehicle based on a vehicle identification code of the target vehicle, wherein the automotive part list comprises customized configuration information of automotive parts of the target vehicle; and determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm, to obtain an automotive part identification serial number of the determined damaged automotive part.

Abstract: A system and method for camera-based heart rate tracking. The method includes: determining bit values from a set of bitplanes in a captured image sequence that represent the HC changes; determining a facial blood flow data signal for each of a plurality of predetermined regions of interest (ROIs) of the subject captured by the images based on the HC changes; applying a band-pass filter of a passband approximating the heart rate to each of the blood flow data signals; applying a Hilbert transform to each of the blood flow data signals; adjusting the blood flow data signals from revolving phase-angles into linear phase segments; determining an instantaneous heart rate for each the blood flow data signals; applying a weighting to each of the instantaneous heart rates; and averaging the weighted instantaneous heart rates.

Abstract: A method of segmenting an MR organ volume includes performing regional mapping on the MR organ volume using a spatial prior probability map of a location of the organ to create a regionally mapped MR organ volume, and performing boundary refinement on the regionally mapped MR organ volume using a level set framework that employs the spatial prior probability map and a propagated shape constraint to generate a segmented MR organ volume.

Abstract: Face image data is acquired and a face image is captured, and a difference between a face image indicated by the face image data and the face image that is captured or a candidate of the difference is detected on the basis of at least one of the face image indicated by the face image data that is acquired, and the face image that is captured. Guidance is acquired on the basis of the difference or the candidate of the difference which is detected, and an output unit is controlled to output the guidance.

Abstract: A system and related method for retrieving, for a first image structure (S1) in an initial image (IG1), a corresponding image structure (S2) in a second image (IG2). The system accepts as input a location of the first structure (S1) in the initial image (IG1) along with an additional structure property such as spectral information to so reduce ambiguity.

Abstract: There is provided an image registration device and an image registration method. The device includes: a feature extractor configured to extract, from a first image, a first feature group and to extract, from a second image, a second feature group; a feature converter configured to convert, using a converted neural network in which a correlation between features is learned, the extracted second feature group to correspond to the extracted first feature group, to obtain a converted group; and a register configured to register the first image and the second image based on the converted group and the extracted first feature group.

Abstract: Techniques related to implementing convolutional neural networks for object recognition are discussed. Such techniques may include generating a set of binary neural features via convolutional neural network layers based on input image data and applying a strong classifier to the set of binary neural features to generate an object label for the input image data.

Abstract: A method and apparatus is provided to iteratively reconstruct a computed tomography (CT) image using a spatially-varying content-oriented regularization parameter, thereby achieving uniform statistical properties within respective organs/regions and different statistical properties (e.g., degree of smoothing and noise level) among the respective organs/regions. For example, less smoothing and sharper features/resolution can be applied within a lung region than within a soft-tissue region by using a smaller regularization parameter value in the lung region than in the soft-tissue region. This can be achieved, e.g., using a minimum intensity projection to suppress/eliminate sub-solid nodules in the lung region. The content-oriented regularization parameter can be generated by reconstructing an initial CT image, which is then segmented/classified according to organs and/or tissue type.

Abstract: An image detection method for determining the posture of a user includes: obtaining a reference image of the user in a region of interest (ROI); obtaining a test image of user at the ROI; executing a feature matching analysis of the test image which compares the feature parameter of the test image and the feature parameter of the reference image to determine the similarity information of the test image and the reference image; and executing a pixel distribution analysis of the test image to obtain user pixel distribution information; and determining the posture of the user based on the user similarity information and the user pixel distribution information.

Abstract: An apparatus, method and computer program product are provided for predicting feature space decay using variational auto-encoder networks. Methods may include: receiving a first image of a road segment including a feature disposed along the road segment; applying a loss function to the feature of the first image; generating a revised image, where the revised image includes a weathered iteration of the feature; generating a predicted image using interpolation between the image and the revised image of a partially weathered iteration of the feature; receiving a user image, where the user image is received from a vehicle traveling along the road segment; correlating a feature in the user image to the partially weathered iteration of the feature in the predicted image; and establishing that the feature in the user image is the feature disposed along the road segment.