Abstract: A road recognition method and system based on a seed point includes: obtaining a remote sensing image; obtaining a grayscale image; inserting a seed point in the grayscale image; searching for four initial road boundary points using the seed point as a reference point; obtaining a smallest bounding rectangle search box formed by the four initial road boundary points; obtaining a plurality of candidate search boxes based on the obtained search boxes; determining whether a sum of squares of grayscale differences between the plurality of candidate search boxes and the obtained search box is greater than a preset threshold; and if yes, stopping searching and completing road recognition; or if not, selecting a new search box from the plurality of candidate search boxes, and retrieving a plurality of candidate search boxes based on the new search box.

Abstract: Imaging data (20) are acquired by a PET scanner (6) or other imaging device. Iterative image reconstruction of the imaging data is performed to generate a reconstructed image (22). The iterative image reconstruction includes performing an update step (24) that includes an edge preserving prior (28) having a spatially varying edge preservation threshold (30) whose value at each image voxel depends on a noise metric (32) in a local neighborhood of the image voxel. The noise metric may be computed as an aggregation of the intensities of neighborhood image voxels of the reconstructed image in the local neighborhood of the image voxel. The edge preserving prior may be a Relative Difference Prior (RDP). For further noise suppression, during the iterative image reconstruction image values of image features of the reconstructed image that have spatial extent smaller than a threshold (38) may be reduced.

Abstract: In one aspect a computer-implemented method of processing a content item to extract information from the content item comprises steps of: receiving the content item at a processing stage; and determining whether the content item satisfies a predetermined content condition, by i) providing content of the content item to a plurality of content analysers, each of which applies machine learning content analysis thereto, in order to make an independent determination of whether that predetermined content condition is satisfied, and provides a confidence score for that independent determination, and ii) making an overall determination of whether the content item satisfies that predetermined content condition based on the confidence scores provided by the content analysers for their respective independent determinations.

Abstract: Current cancer screening methods are not suitable to be applied on a broad scale and are not transparent to the patient. The problem is solved by a method to determine a degree of abnormality, the method comprising the following steps: receiving a whole slide image, the whole slide image depicting at least a portion of a cell, classifying at least one image tile of the whole slide image using a neural network to determine a local abnormality degree value associated with the at least one image tile, the local abnormality degree value indicating a likelihood that the associated at least one segment depicts at least a part of a cancerous cell, and determining a degree of abnormality for the whole slide image based on the local abnormality degree value for the at least one image tile.

Abstract: A system for determining blockage of a vehicle camera is configured to apply a partition grid having a plurality of locations to a sequence of images to form a plurality of regions. The system determines at least one spatial feature corresponding to the partition grid and at least one temporal feature corresponding to the partition grid. The system generates a sequence of classifications for each location of the plurality of locations based on the at least one spatial feature, the at least one temporal feature, and reference information. The system applies a smoothing technique to determine a subset of regions that are blocked among the sequence of classifications, and generates an output signal based on the subset of regions. The output may be provided to an output system to wash the camera lens, notify the user or the vehicle of the blockage, or modify image processing.

Abstract: A communications system comprises a maximum ratio combining (MRC) circuit for receiving a plurality of input data streams and for processing the plurality of input data streams using maximum ration combining to improve signal to noise ratio. A MIMO transmitter transmits the MRC processed carrier signal over a plurality of separate communications links from the MIMO transmitter, each of the plurality of separate communications links from one transmitting antenna of a plurality of transmitting antennas to each of a plurality of receiving antennas at a MIMO receiver.

Abstract: An electronic apparatus operated by a sales clerk includes a display, a camera configured to capture an image of a code displayed on a screen of a portable registration apparatus operated by a customer in a store, the code corresponding to one or more commodities to be purchased and check data indicating whether each of said one or more commodities needs to be checked by the sales clerk before being checked out, and a processor configured to, when the image of the code is captured by the camera, acquire information indicating said one or more commodities to be purchased and the check data using the code, and control the display to display a screen showing one or more commodities that need to be checked by the sales clerk based on the acquired information.

Abstract: A progressive localization method for text-to-video clip localization. The method comprises: first, respectively extracting features of two modes, namely a video mode and a text mode by using different feature extraction methods; then progressively selecting different step sizes, and learning the correlation between the video and the text in multiple stages; and finally, training a model in an end-to-end manner based on the correlation loss of each stage. Moreover, the fine time granularity stage is fused with information of the coarse time granularity stage by means of a condition feature update module and up-sampling connection, such that different stages are mutually promoted. Different stages can pay attention to clips with different time granularities, and the model can cope with the situation that the length of a target clip is obviously changed based on the interrelation between the stages.

Abstract: Disclosed in the present invention is hyperspectral image classification method based on context-rich networks. The method comprises a training stage and a prediction stage, wherein the training stage comprises image pre-processing, sample selection and network training. Firstly, performing normalization on a hyperspectral image, and then randomly selecting an appropriate proportion of marked samples from each category to generate a label map, and performing training by using the designed network; in the prediction stage, directly inputting the whole image into the trained network and obtaining a final classification result. By means of the present invention, data pre-processing, feature extraction, the process of context-rich information capturing, and classification are taken into comprehensive consideration in the whole flow; and the classification of a hyperspectral image is realized by means of constructing an end-to-end network.

Abstract: A system for identifying biomarkers in a digital image of a Hematoxylin and Eosin-stained slide of a target tissue includes a processor and an electronic network; and a memory having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: process segmented tile images determine a predicted biomarker presence; and transmit the predicted presence. A non-transitory computer-readable medium includes a set of computer-executable instructions that, when executed by one or more processors, cause a computer to: process segmented tile images; determine a predicted biomarker presence; and transmit the predicted presence. A computer-implemented method includes processing segmented tile images; determining a predicted biomarker presence; and transmitting the predicted presence.

Abstract: A method of characterizing a serum or plasma portion of a specimen in a specimen container provides a fine-grained HILN index (hemolysis, icterus, lipemia, normal) of the serum or plasma portion of the specimen, wherein the H, I, and L classes may each have five to seven sub-classes. The HILN index may also have one un-centrifuged class. Pixel data of an input image of the specimen container may be processed by a deep semantic segmentation network having, in some embodiments, more than 100 layers. A small front-end container segmentation network may be used to determine a container type and boundary, which may additionally be input to the deep semantic segmentation network. A discriminative network may be used to train the deep semantic segmentation network to generate a homogeneously structured output. Quality check modules and testing apparatus configured to carry out the method are also described, as are other aspects.

Abstract: A method for training a face detection model, including: acquiring a training face image; performing three-dimensional reconstruction on the training face image based on a preset three-dimensional face model, and acquiring a training three-dimensional face model; generating a training UV coordinate map including three-dimensional coordinates of the training three-dimensional face model based on the training three-dimensional face model; and training a semantic segmentation network by using the training face image and the training UV coordinate map, and acquiring a face detection model. The face detection model is configured to generate a UV coordinate map including three-dimensional coordinates.

Abstract: In one or more embodiments, one or more systems, one or more methods, and/or one or more processes may determine that a user is in a presence of an information handling system (IHS); determine a digital image of a face of the user; determine an angle of the face of the user with respect to a vertical axis of a camera based at least on the digital image; determine that the face is facing a display associated with the IHS; determine an amount of time, which the user spends looking at the display; determine, via multiple sensors associated with the IHS, a heart rate and a respiratory rate associated with the user; determine that the user should move based at least on the first amount of time, the heart rate, the respiratory rate, and the angle; and display information indicating that the user should move.

Abstract: A cortical malformation identification method includes quantitatively evaluating, using a processor of a computer that includes the processor and a memory, digital image data from a magnetic resonance imaging (MRI) scan on a cerebral cortex to produce quantified scan data. The method also includes automatically detecting a cortical malformation based on the quantified scan data. An image of the cerebral cortex may be color-coded so that the cortical malformation is shown in a different color than the remainder of the cerebral cortex in the image, based on the quantified scan data. Additionally or alternatively, a 3-dimensional representation of the cerebral cortex may be mapped to the quantified scan data to produce a mapped image of the cerebral cortex including the detected cortical malformation.

Abstract: Embodiments of this application provide a method for detecting a target point in an image. The method may include: obtaining an image under test, where the image under test may include a structure-stable first target object and a structure-unstable second target object; and processing the image under test based on a target point detection model to obtain a target point in the image under test, where the target point may include a feature point on the structure-stable first target object and a feature point on the structure-unstable second target object.

Abstract: Embodiments of this application disclose an image description generation method performed at a computing device. The method includes: obtaining a target image; generating a first global feature vector and a first label vector set of the target image; generating a first multi-mode feature vector of the target image through a matching model, the matching model being a model obtained through training according to a training image and reference image description information of the training image; and applying the first multi-mode feature vector, the first global feature vector, and the first label vector set to a computing model, to obtain the target image description information, the computing model being a model obtained through training according to image description information of the training image and the reference image description information.

Abstract: A computer device obtains a plurality of medical images. The device generates a texture image based on image data of a region of interest in the medical images. The device extracts a local feature from the texture image using a first network model. The device extracts a global feature from the medical images using a second network model. The device fuses the extracted local feature and the extracted global feature to form a fused feature. The device performs image classification based on the fused feature.

Abstract: Systems, apparatuses and methods may provide for conducting an importance measurement of a plurality of parameters in a trained neural network and setting a subset of the plurality of parameters to zero based on the importance measurement. Additionally, the pruned neural network may be re-trained. In one example, conducting the importance measurement includes comparing two or more parameter values that contain covariance matrix information.

Abstract: A whiteboard cleaning system includes a user movement sensor that determines when a user is inactive; a whiteboard capture camera that makes an image of the whiteboard when the user movement sensor detects that the user is inactive; a classification module that classifies the image with a pre-trained image data set using an augmentation technique to enhance the size of the image data set and determines whether the whiteboard needs to be cleaned based on the classification, through transfer learning, using the image data set; and a wiper that cleans the whiteboard when the classification module determines that the whiteboard needs to be cleaned.

Abstract: A method to reconstruct images from raw MRI data, and recover an image by solving an optimization problem. Hence, the method is an image reconstruction system for image recovery contrary to similar methods, the method reconstructs all images using both joint and individual objective functions. The method includes: acquiring with the MRI system, multiple images under an influence of different contrast mechanisms, wherein the different contrast mechanisms belong to a same anatomy, solving an optimization problem with an optimization algorithm using both joint and individual objective functions simultaneously for each of multiple image contrasts or a subset of the multiple image contrasts, to reconstruct the multiple images from acquired data.