Abstract: A method and apparatus for determining a slope of a road using a side view camera of a vehicle, the method includes identifying a road image collected from a side view camera, dividing the road image into a plurality of regions, calculating a slope of a road for each of the plurality of regions based on driving lanes comprised in each of the plurality of regions, and determining a slope between the side view camera and the road using the slope of the road calculated for each of the plurality of regions.

Abstract: A method for skeletonizing the strands of a composite material part in a 3D image having a step of detecting oriented section centers of the strands and a link from each center to the closest center having the same orientation, the detection being carried out by means of at least one reference volume having an oriented centered strand pattern, the detection step having, for each reference volume: •a step of determining portions of the image, •a step of calculating a correlation score between the reference volume and each portion associated with the central voxel of each portion, so as to obtain a correlation score for each voxel of the image; and •a step of determining the strand centers corresponding to the voxels having a correlation score which corresponds to a local maximum.

Abstract: A system and method for performing visual odometry is disclosed. In aspects, the system implements methods to generate an image pyramid based on an input image received. A refined pose prior information representing a location and orientation of the autonomous vehicle can be generated based on one or more images of the image pyramid. One or more seed points can be selected from the one or more images of the image pyramid. One or more refined seed representing the one or more seed points with added depth values can be generated. One or more scene points can be generated based on the one or more refined seed points. A point cloud can be generated based on the one or more scene points.

Abstract: Synthesizing training data for training a change detection model includes receiving a patched image comprising a background image with a patch pasted into the background image. It further includes synthesizing a harmonized patched image at least in part by harmonizing the patched image using a machine learning model trained on the background image. It further includes providing as output a synthetic training sample usable to train a change detection model. The synthetic training sample includes a reference image, at least a portion of the harmonized patched image, and a corresponding mask.

Abstract: A computer implemented method of training a neural network configured to combine a set of coefficients with respective input data values. So as to train a test implementation of the neural network, sparsity is applied to one or more of the coefficients according to a sparsity parameter, the sparsity parameter indicating a level of sparsity to be applied to the set of coefficients; the test implementation of the neural network is operated on training input data using the coefficients so as to form training output data; in dependence on the training output data, assessing the accuracy of the neural network; the sparsity parameter is updated in dependence on the accuracy of the neural network; and a runtime implementation of the neural network is configured in dependence on the updated sparsity parameter.

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure identify a plurality of candidate concepts in a knowledge graph (KG) that correspond to an image tag of an image; generate an image embedding of the image using a multi-modal encoder; generate a concept embedding for each of the plurality of candidate concepts using the multi-modal encoder; select a matching concept from the plurality of candidate concepts based on the image embedding and the concept embedding; and generate association data between the image and the matching concept.

Abstract: Techniques for facilitating non-uniformity mitigation for imaging systems and methods are provided. In one example, a method includes cropping an image based on a defect in the image to obtain a cropped image. The method further includes cropping a supplemental flat field correction (SFFC) map based on the defect in the image to obtain a cropped SFFC map. The method further includes determining a scaling value of a scaling term based at least on a cost function. The method further includes scaling the SFFC map based on the scaling value to obtain a scaled SFFC map. Related devices and systems are also provided.

Abstract: An appropriate skin color range can be promptly set. An image processing apparatus configured to estimate a pulse of a person detected from an image includes a setting unit configured to set an ellipse region including a face detected from the image, an acquisition unit configured to acquire color information about a pixel included in the set ellipse region, a determination unit configured to determine whether the acquired color information satisfies a predetermined condition, and a specifying unit configured to specify a threshold value indicating a skin color range based on the color information in the ellipse region in a case where the determination unit determines that the acquired color information satisfies the predetermined condition.

Abstract: A method for training a classifier and/or regressor. The method includes: providing training samples labelled with ground truth classification and/or regression scores; and for each training sample from at least a subset of the training samples: determining a confidence score that quantifies an uncertainty of the training sample, and/or an ease or difficulty of classifying this sample, and reducing a largest ground truth classification and/or regression score with respect to one class and/or regression value by an amount that is dependent on the confidence score, and distributing the amount to ground truth classification and/or regression scores with respect to other classes and/or regression values; mapping the training samples to classification and/or regression scores; rating a deviation of the classification and/or regression scores from the updated ground truth classification and/or regression scores; and optimizing parameters that characterize the behavior of the classifier and/or regressor.

Abstract: A reconstruction system is presented for reconstructing morphology of biological cells. The system includes data input and output utilities, memory, and a data processor, and is configured for data communication with an image data provider to receive raw image data comprising a sequence of image frames acquired from the cell during a movement of the cell and being indicative of optical path delay (OPD) of light propagation through the biological cell. The data processor is configured and operable to process the raw image data and determine 3D dynamic morphological data of the cell. The data processor includes: a modeling utility; a position recovery module; and an analyzer module.

Abstract: A learning image generation device including: a supervised data acquisition unit that acquires supervised data including a learning image and a correct learning image in which a correct region is defined in the learning image as a pair; and a variation learning image generation unit that generates a variation learning image in which a pixel value of a pixel belonging to the correct region is varied within a limitation range of an allowable pixel value of the pixel belonging to the correct region in the learning image.

Abstract: A learning processing device that is based on a neural network model and image data obtained by capturing an image of the object to be inspected, and constructs the neural network model used for inspecting the object to be inspected. The learning processing device is provided with a learning unit which performs a learning process under a prescribed learning condition on the basis of a list of the image data including a plurality of learning images and constructs the neutral network model. The learning unit embeds unique model identification data in the neural network model, whenever the neural network model is constructed.

Abstract: A data-driven method and system using optical tracking of natural facial features for quick and accurate pose determination during scanning using one or more cameras installed within or on a PET-CT gantry. No patient preparation, fixtures, or artificial features are needed. The pose data is analyzed and incorporated iteratively in reconstruction for reconstruction to motion correct the PET data. The present invention thus results in improved correction of blurring and artifacts caused by head motion during the PET scan.

Abstract: When acquiring detailed utilization information from imaging equipment in a cross-vendor approach, one or more sensors (16, 18, 22, 24) are positioned within a data security zone (14) in which an imaging procedure is performed. Sensor data is pre-processed on an isolated processing unit (20) to remove any sensitive information and keep a selection of features only. The resultant feature pattern is transmitted outside of the data security zone to a processing unit (28) where pattern recognition is performed on feature pattern to identify the type of imaging modality, scan, etc. being performed as well as to determine whether the scan is being performed according to schedule.

Abstract: Methods and systems are provided for identifying motion in medical images. In one example, a method includes obtaining projection data of an imaging subject, reconstructing a first image of a location of the imaging subject from the projection data using a first reconstruction technique and reconstructing a second image corresponding to the same location of the imaging subject from the of projection data using a second reconstruction technique, different than the first reconstruction technique in terms of temporal sensitivity, calculating an inconsistency metric quantifying temporal inconsistencies between the first image and the second image, and taking an action based on the inconsistency metric.

Abstract: Image processing is described. An example method includes generating a feature extraction layer portion of an image classification model based on a deep neural network (DNN) model, and extracting features of a group of images by using the feature extraction layer portion. The method further includes training an output layer portion of the image classification model according to the features of training images in the group of images and classification labels of the training images. The method further includes generating the image classification model by combining the feature extraction layer portion and the output layer portion. Embodiments of the present disclosure implement a lightweight artificial intelligence (AI) solution on a storage system. An expanded storage system can facilitate the generation of AI applications and assist in training an image classification model more quickly, and the obtained image classification model can also produce high accuracy on a small training set.

Abstract: An image processing apparatus for performing image quality processing on an image includes: a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: obtain a first image by downscaling an input image by using a downscale network; extract first feature information corresponding to the first image by using a feature extraction network; obtain a second image by performing image quality processing on the first image based on the first feature information, by using an image quality processing network; and obtain an output image by upscaling the second image, extracting second feature information corresponding to the input image, and performing image quality processing on the upscaled second image based on the second feature information, by using an upscale network.

Abstract: A method includes receiving data indicative of an image of a face of an unknown user of the computing device while the computing device is in a reduced access mode locked state. The method also includes determining whether the unknown user is the known user by at least comparing the image of the face of the unknown user to one or more images of a plurality of images of a face of a known user of the computing device. The method further includes setting the computing device to an increased access mode in response to determining that the unknown user is the known user.

Abstract: A system and method for performing image processing. The method includes receiving an image of a first modality and a real image of a second modality, the image of the first modality and the image of the second modality capturing respective images of a same subject, applying a first trained model to the image of the first modality to generate an artificial image mimicking the image of the second modality, applying a second trained model to the artificial image mimicking the image of the second modality and data of the image of the first modality, and outputting at least one conclusion regarding the generated artificial image.

Abstract: An image reconstruction method includes: determining singles rates of radiation detectors in a frame of imaging data detected by the radiation detectors; determining an energy correction factor (Nwgt) for each radiation detector based on an energy spectrum distribution of gamma rays incident on the radiation detector during acquisition of the frame of imaging data; determining a singles live time correction factor for each radiation detector from the singles rate and the energy correction factor; determining a system coincidence live time correction factor from the system singles rate; for each line of response (LOR) connecting pairs of radiation detectors, determining a live time correction factor for the LOR from the determined singles live time correction factors of the pair of radiation detectors connected by the LOR and the determined system coincidence live time correction factor; and reconstructing the frame of imaging data using the determined LOR live time correction factors.