Abstract: Provided is a method that addresses a problem of classifying cells through use of cell autofluorescence, the method including the steps of: acquiring autofluorescence information regarding a plurality of cells through use of an autofluorescence image regarding the plurality of cells; acquiring region information; extracting the autofluorescence information on individual cells from the autofluorescence information regarding the plurality of cells and the region information; and classifying the plurality of cells into two or more groups by performing clustering through use of the autofluorescence information on the individual cells.

Abstract: Examples described herein provide a method that includes performing an image analysis on an image of a layer of an object being manufactured by an additive manufacturing system to identify an exposed surface in the image of the layer. The method further includes performing a build simulation to generate a simulated distortion for the layer. The method further includes evaluating build data to determining a value of an influencing factor for the layer. The method further includes predicting at least one of a predicted distortion or a predicted re-coater interference for a next layer, using a machine learning model, based at least in part on the image analysis, the build simulation, and the build data. The method further includes implementing an action, based at least in part on the at least one of the predicted distortion or the predicted re-coater interference, to alter fabrication of the next layer.

Abstract: An image analysis server, an object counting method using the image analysis server, and an object counting system are provided, in which the object counting method using the image analysis server includes, by a user terminal, inputting an image including one or more objects, by an image analysis server, forming a plurality of boxes for each of the objects, and keeping only the number of boxes corresponding to the objects and deleting the other boxes of the plurality of boxes, and by the image analysis server, counting the number of the remaining boxes and transmitting the corresponding number of the boxes to the user terminal.

Abstract: Methods and systems for computing a surface normal vector for a point cloud are disclosed. A sparse range map is generated by projecting the point cloud. A vertical kernel and a horizontal kernel are used to generate a vertical kernel range map and a horizontal kernel range map from the sparse range map. To complete an empty entry in the sparse range map, a guidance range map is used compute a vertical gradient and a horizontal gradient. The empty entry is filled using a corresponding entry in the vertical kernel range map or in the horizontal kernel range map, based on a comparison between the vertical gradient and the horizontal gradient. A surface normal vector is computed using the completed dense range map.

Abstract: An image processing method includes using different filter weights to process a multi-scale feature map obtained by encoding an initial image to obtain a target residual image after obtaining the initial image, and performing target processing on the initial image and the target residual image to obtain a target output image.

Abstract: A method and device for generating an all-in-focus image are disclosed. A method of generating an all-in-focus image includes obtaining a scene image and a phase detection image by capturing a scene using a phase detection image sensor; determining a blur kernel based on the phase detection image and a particular mapping relationship indicating a depth and a blur kernel distribution; and generating the all-in-focus image by deblurring the scene image using the blur kernel.

Abstract: A method of monitoring synthetic gas emissions comprises obtaining a gas concentration image within a first area of interest from an overhead image acquisition device, detecting from the gas concentration image at least one gas plume of a synthetic gas emission, quantifying an emission rate of the detected gas plume, estimating an estimated point source of the detected gas plume, and attributing the detecting gas plume to an actual point source. A corresponding system for monitoring synthetic gas emissions comprises a memory storing a gas concentration image of a first area of interest, and a processor communicatively coupled thereto and configured to detect from the image of the gas concentration at least one gas plume of a synthetic gas emission, quantify an emission rate of the detected gas plume, estimate an estimated point source of the detected gas plume, and attribute the detecting gas plume to an actual point source.

Abstract: A product detection device is provided with: an image acquisition unit; a binarization unit; and a detection unit. The image acquisition unit acquires an image of shelves for displaying products. The binarization unit binarizes a region in the image into a product region where products are imaged and a non-product region where things other than the products are imaged. The detection unit detects the display state of products displayed on the shelves in accordance with the width of the binarized product region and the width of a gap region adjacent to the products.

Abstract: The luminances of an image are not only optimized for a particular maximum displayable luminance of a display, but also for a particular amount of light in the viewing environment in which the display is watched. A method of processing an input image to obtain an output image includes receiving a reference luminance mapping function as metadata associated with an input image, calculating an adapted luminance mapping function on the reference luminance mapping function; calculating a control parameter that specifies how much the adapted luminance mapping function deviates from the reference luminance function and is based on a maximum luminance of a display and a black level of the display; and applying the adapted luminance mapping function to at least a portion of the input pixel luminances so as to obtain output luminances for at least a portion of pixels of the output image.

Abstract: A method according to the present disclosure includes selecting a reference class from a plurality of classes, calculating a plurality of degrees of similarity between a feature spectrum corresponding to target training data and a plurality of the feature spectra belonging to the reference class, applying, to the plurality of degrees of similarity, a defectiveness function that is determined in advance, and calculating a defectiveness index with respect to the target training data, and determining whether the target training data is the defective data, based on a result of comparison between the defectiveness index and a threshold value.

Abstract: Disclosed herein are methods, systems, and computer-readable media for generating and using unbinned image data, characterized by (a) receiving image data corresponding to an image; (b) generating the unbinned image data by performing an unbinning operation on the received image data, wherein the unbinning operation is characterized by conditions of invertibility and smoothness; and (c) using the unbinned image data for either: (i) displaying a version of the image based on the unbinned image data; and/or (ii) performing image processing.

Abstract: A method for tracking a position of an object in a scene surrounding a mobile machine based upon information acquired from monocular images, includes: acquiring at least a first image at a first time and a second image at a second time, the first image and the second image each including image data corresponding to the object and a scene feature present in the scene surrounding the mobile machine; detecting the object in the first image and the second image; matching the scene feature across the first image and the second image; performing an estimation of an egomotion of the mobile machine based upon the scene feature matched across the first image and the second image; and predicting a position of the object taking into account the estimation of the egomotion of the mobile machine.

Abstract: A computing system can obtain wafer images of integrated circuitry having physical structures and classify each of the wafer images based on image characteristics of the wafer images. The computing system can partition each of the wafer images into a plurality of blocks, analyze each of the blocks to determine which of the blocks correspond to a background portion or a contour portion of the wafer images, assign an image score to each wafer image based on the analysis of each of the blocks, and classify the wafer images based on the image scores assigned to the wafer images. The computing system can set parameters for contour extraction using at least one of the wafer images selected from each of the classifications of the wafer images, and extract contours corresponding to the physical structures of the integrated circuitry from the wafer images based, at least in part, on the parameters.

Abstract: A system and method for creating a composite retinal thickness map of an eye, including collecting, by an optical coherence tomography (OCT) device, a set of a plurality of optical coherence tomography (OCT) volume scans of the eye. At least one set of the plurality of OCT volume scans is collected by the OCT device.

Abstract: Disclosed are an apparatus and method for measuring a dimension. The method of measuring a dimension according to an aspect of the present invention includes photographing a target object and generating an image, normalizing the image of the target object, generating normalized estimated dimension information about the target object from the normalized image of the target object using a pre-trained dimension prediction model, and converting the normalized estimated dimension information of the target object into estimated dimension information of the target object.

Abstract: Broadly speaking, embodiments of the present techniques provide a method for reducing errors in the outputs of machine learning, ML, models on a potential output of the models to resolve any inconsistencies before outputting a final result from the models. The final result respects a set of rules or constraints, which may include logical constraints. Advantageously, this reduces the risk of a model outputting a result which violates some rules associated with the overall task of the model, which could be dangerous or provide a poor user experience.

Abstract: Disclosed are a point cloud encoding and decoding method and device based on a two-dimensional regularization plane projection. The encoding method includes: acquiring original point cloud data; performing two-dimensional regularization plane projection on the original point cloud data to obtain a two-dimensional projection plane structure; obtaining a plurality of pieces of two-dimensional image information according to the two-dimensional projection plane structure; and encoding the plurality of pieces of two-dimensional image information to obtain code stream information.

Abstract: An image recognition method and system for a display panel, a training method, and an electronic device and a non-volatile computer-readable storage medium. The image recognition method includes: acquiring an image of a display panel, wherein the image includes gate lines extending in a first direction and data lines extending in a second direction, the gate lines and the data lines intersecting to define a plurality of sub-pixel regions, and the image further includes a defect pattern; and recognizing the defect pattern in the image by using an image recognition model to obtain defect information, wherein the defect information includes at least one of a defect type or a defect position of the defect pattern, the image recognition model comprises a first attention model configured to learn a weight proportion of a feature of the defect pattern in the image.

Abstract: A method of 3D-inspection of a semiconductor object inside of an inspection volume of a wafer or wafer sample comprises a 3D data processing and a step for acquiring a plurality of two-dimensional images. The acquiring step comprises a monitoring step for determining whether a two-dimensional image is in conformity with a desired property of the 3D data processing. The disclosure further comprises a method of configuring the method of 3D-inspection and a system configured to execute the method of 3D-inspection as well as the method of configuring the method of 3D-inspection.

Abstract: One or more embodiments of the present disclosure describe an artificial intelligence assisted substrate defect repair apparatus and method. The AI assisted defect repair apparatus employs an object detection algorithm. Based on the plurality of images taken by detectors located at different respective positions, the detectors capture various views of an object including a defect. The composition information as well as the morphology information (e.g., shape, size, location, height, depth, width, length, or the like) of the defect and the object are obtained based on the plurality of images. The object detection algorithm analyzes the images and determines the type of defect and the recommends a material (e.g., etching gas) and the associated information (e.g., supply time of the etching gas, flow rate of the etching gas, etc.) for fixing the defect.