Abstract: For reconstruction in medical imaging, such as reconstruction in MR imaging, scanning is accelerated by under-sampling. In iterative reconstruction, the input to the regularizer is altered provide for correlation of non-local aliasing artifacts. Duplicates of the input image are shifted by different amounts based on the level of acceleration. The resulting shifted images are used to form the input to the regularizer. Providing an input based on shifts allows the regularization to suppress non-local as well as local aliasing artifacts.

Abstract: A method for automated, artificial-intelligence-based denudation includes scanning, robotically, a dish containing a cumulus-oocyte-complex (COC) using an imaging system and an artificial intelligence/machine learning system (AI/ML system) to create an image object. The imaging system includes a microscopy system, a camera system, and a lighting system. The dish includes an enzyme to remove cumulus cells from an oocyte among the COC. The method includes identifying the COC within the image object, and a location, based on comparing the image object to a threshold using the AI/ML system. The threshold is an optical pattern with a probability of corresponding to a COC mass. The method includes instructing a robotic pipettor to collect the COC at the location. The method includes iteratively collecting the COC within the robotic pipettor and expelling the COC to return it to the dish until the AI/ML system confirms sufficient removal of cumulus and corona cells.

Abstract: The present application relates generally to identifying regions of interest in images, including but not limited to whole slide image region of interest identification, prioritization, de-duplication, and normalization via interpretable rules, nuclear region counting, point set registration, and histogram specification color normalization. This disclosure describes systems and methods for analyzing and extracting regions of interest from images, for example biomedical images depicting a tissue sample from biopsy or ectomy. Techniques directed to quality control estimation, granular classification, and coarse classification of regions of biomedical images are described herein. Using the described techniques, patches of images corresponding to regions of interest can be extracted and analyzed individually or in parallel to determine pixels correspond to features of interest and pixels that do not.

Abstract: An image processing sequence generation method includes using a reference table to generate a plurality of image processing sequences so as to have a probability relationship where an input-side sequence element having a high connection reference value with respect to an output-side sequence element has a high connection probability of being connected to the output-side sequence element.

Abstract: Progressive precision image classifier and method of training include storing a dataset of labeled images, training a neural network to generate a classification vector comprising a plurality of confidence values, each confidence value corresponding to a classification, validating the trained neural network, calculating fine-grained confidence thresholds for each classification, wherein each classification represents a leaf-level classification in a hierarchical classification structure, and calculating coarse-level confidence thresholds for at least one parent class in the hierarchical classification structure, wherein each parent class defines a group of at least one leaf-level classification. Each label in the training data identifies a leaf-level classification in the hierarchical classification structure, and the classification vector includes a 1×N vector of confidence values, where N represents a number of leaf-level classifications output by the trained neural network.

Abstract: A method of identifying and recognizing characters using a dual-stage neural network pipeline, the method including: receiving, by a computing device, image data; providing the image data to a first convolutional layer of a convolutional neural network (CNN); applying, using the CNN, pattern recognition to the image data to identify a region of the image data containing text; providing sub-image data comprising the identified region of the image data to a convolutional recurrent neural network (CRNN); and recognizing, using the CRNN, the characters within the sub-image data.

Abstract: In an object tracking device, the extraction means extracts target candidates from images in a time-series. The first setting means sets a first search range based on frame information and reliability of a target in a previous image in the time-series. The tracking means searches the target from the target candidates extracted within the first search range using the reliability indicating similarity to a target model, and tracks the target. The second setting means sets a second search range which includes the first search range and which is larger than the first search range. The model updating means updates the target model using the target candidates extracted within the first search range and the target candidates extracted within the second search range.

Abstract: Systems and methods are provided for point cloud processing with an equivariant neural network and implicit shape learning that may produce correspondence-free registration. The systems and methods may provide for feature space preservation with the same rotation operation as a Euclidean input space, due to the equivariance property, which may provide for solving the feature-space registration in a closed form.

Abstract: Aspects of the disclosure provide methods and apparatuses for point cloud compression and decompression. In some examples, an apparatus for point cloud compression/decompression includes processing circuitry. The processing circuitry determines to use a prediction mode for coding (encoding/decoding) information associated with a current point in a point cloud. In the prediction mode, the information associated with the current point is predicted based on one or more neighbor points of the current point. The processing circuitry calculates, using integer operations, a distance-based weighted average value based on distances of the one or more neighbor points to the current point, and determines the information associated with the current point based on the distance-based weighted average value.

Abstract: A method by one or more computers for learning a machine learning model classifying an input image into known classes and an unknown class by extracting a feature of the input image. The method comprises acquiring a set of features of a plurality of samples of training data each of which is with a label, calculating a loss function based on the set of the features, and learning the machine learning model to reduce the loss function. The loss function is calculated to include a first loss function and a second loss function. The first loss function is configured to become larger as first distances become smaller than a predetermined margin. The second loss function is configured to become larger as second distances become larger and as third distances become smaller.

Abstract: An image processing apparatus, including a processor configured to execute instructions stored in a memory to: obtain characteristic information of a first image, divide the characteristic information into a plurality of groups, input each group into a respective layer of a plurality of layers included in a convolutional neural network and perform a convolution operation using one or more kernels to obtain a plurality of pieces of output information, generate an attention map including weight information corresponding to each pixel included in the first image, based on the plurality of pieces of output information, generate a spatially variant kernel including a kernel corresponding to the each pixel, based on the attention map and a spatial kernel including weight information according to a position relationship between the each pixel and a neighboring pixel, and generate a second image by applying the spatially variant kernel to the first image.

Abstract: Techniques disclosed herein relate to identifying individuals in digital images. In some embodiments, a digital image may be acquired (802) that captures an environment containing at least a first subject. A first portion of the digital image depicting the first subject may be segmented (806) into a plurality of superpixels. For each superpixel of the plurality of superpixels: a semantic label may be assigned (810) to the superpixel; features of the superpixel may be extracted (812); and a measure of similarity between the features extracted from the superpixel and features extracted from a reference superpixel identified in a reference digital image may be determined (814), wherein the reference superpixel has a reference semantic label that matches the semantic label assigned to the superpixel. Based on the measures of similarity associated with the plurality of superpixels, it may be determined (818) that the first subject is depicted in the reference image.

Abstract: A method and system may survey a property using aerial images captured from an unmanned aerial vehicle (UAV), a manned aerial vehicle (MAV) or from a satellite device. The method may include identifying a commercial property for a UAV to perform surveillance, and directing the UAV to hover over the commercial property and capture aerial images at predetermined time intervals. Furthermore, the method may include receiving the aerial images of the commercial property captured at the predetermined time intervals, detecting a surveillance event at the commercial property, generating a surveillance alert, and transmitting the surveillance alert to an electronic device associated with an owner of the commercial property.

Abstract: A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the method includes tiling at least one region of interest of the input image into a set of tiles. For each tile, the method includes extracting a feature vector of the tile by applying a convolutional neural network, wherein a feature is a local descriptor of the tile; and computing a score of the tile from the extracted feature vector, said tile score being representative of a contribution of the tile into a classification of the input image. The method also includes sorting a set of the tile scores and selecting a subset of the tile scores based on their value and/or their rank in the sorted set. The method also includes applying a classifier to the selected tile scores in order to classify the input image.

Abstract: An apparatus for evaluating color of an object includes an acquisition unit configured to acquire image data which is acquired by imaging the object and a color chart group including color charts having different reflectance within a one angle of view, an estimation unit configured to estimate a value of reference white under an exposure condition corresponding to the imaging based on the image data, and a calculation unit configured to calculate a color value for evaluating the color of the object based on the image data and the estimated value of the reference white.

Abstract: A scattering tomography device includes: a transmitting antenna element that transmits radio waves into an object from outside; a receiving antenna element that receives, outside the object, scattered waves of the radio waves transmitted into the object; and an information processing circuit that generates an image of the interior of the object using measurement data indicating the scattered waves received by the receiving antenna element. The information processing circuit: derives, using the measurement data, a relational expression that satisfies an equation whose solution is a scattering field function; derives, using the relational expression, an image function that is for generating the image and includes one or more parameters indicating a correspondence between a change in frequency of the radio waves and a change in a dielectric constant of the object in accordance with Debye relaxation; and generates the image using the image function.

Abstract: A method including receiving a first set of one or more street level images of houses into a Machine Learned Model trained with a second set of street level images with one or more exterior features of the houses labeled, identifying the one or more exterior features in the first set of street level images by way of the Machine Learned Model, and quantifying and outputting the counts and/or two-dimensional areas for each of the identified exterior features in the first set of one or more street level images is described. Non-transitory, computer-readable storage media having instructions for executing the method steps by one or more processors as well as computer or computer systems capable of performing the method steps are also described.

Abstract: A target detection method and apparatus. The method comprises: acquiring an input image, and sending same to a candidate region generation network to generate a plurality of regions of interest; formatting the plurality of regions of interest, and then sending same to a target key point network to generate a thermodynamic diagram; using a global feature map of the input image to perform convolution on the thermodynamic diagram, so as to generate a local depth feature map; and fusing the global feature map and the local depth feature map, and detecting a target therefrom by means of a detector. The present invention can be applied to target detection at different scales, improves the detection accuracy and robustness of a target detection technique for an occluded target in complex scenarios, and achieves, by means of making full use of local key point information of the target, target positioning under occlusion.

Abstract: A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the method includes tiling at least one region of interest of the input image into a set of tiles. For each tile, the method includes extracting a feature vector of the tile by applying a convolutional neural network, wherein a feature is a local descriptor of the tile; and computing a score of the tile from the extracted feature vector, said tile score being representative of a contribution of the tile into a classification of the input image. The method also includes sorting a set of the tile scores and selecting a subset of the tile scores based on their value and/or their rank in the sorted set. The method also includes applying a classifier to the selected tile scores in order to classify the input image.

Abstract: Crop loss estimation allows a user to monitor and estimate damage to the crops due to various natural events/factors. State of the art systems used for the crop loss estimation have the disadvantage that they do not convey to the users extent of damage. In addition to this, the existing methods do not take into account the recovery factor of the crops due to multiple factors and end up in overestimating the loss. The disclosure herein generally relates to crop monitoring, and, more particularly, to a method and system for crop loss estimation. In this method, crop loss is assessed based on real-time weather parameters and remote sensing data collected and processed, and crops are classified as being in one of a repairable damage class and a permanent damage class. The system also quantifies the crop loss, which allows the user to understand magnitude of the crop loss.