Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for image segmentation and chemical analysis using machine learning. In some implementations, a system obtains a hyperspectral image that includes a representation of an object. The system segments the hyperspectral image to identify regions of a particular type on the object. The system generates a set of feature values derived from image data for different wavelength bands that is located in the hyperspectral image in the identified regions of the particular type. The system generates a prediction of a level of one or more chemicals in the object based on an output produced by a machine learning model in response to the set of feature values being provided as input to the machine learning model. The system provides data indicating the prediction of the level of the one or more chemicals in the object.

Abstract: An intelligent monitoring system for waste disposal and the method thereof are provided, which include a plurality of operational devices and stages. First, a transportation stage is performed to loading a transport vehicle with a waste so as to transport the waste to a disposal station for further treatment. A camera and a sensor for detecting abnormal conditions are installed any one of the operational devices or installed in the operational path of any one of the operational devices. The camera records the videos of the operational stages, captures the images from the videos and recognizes the images in order to determine whether the abnormal conditions occur in any one of the operational stages. Alternatively, the camera is triggered to capture the images and recognize the images after the abnormal conditions are detected by the sensor in order to determine whether the abnormal conditions actually occur.

Abstract: Traditional food quality monitoring systems fail to monitor the variation of food quality in real-time scenarios. Existing machine learning approaches require dedicated data models for different classes of food items due to differences in characteristics of different food items. Also, to generate such data models, a lot of annotated data is required per food item, which are expensive. The disclosure herein generally relates to monitoring and shelf-life prediction of food items, and, more particularly, to system and method for real-time monitoring and shelf-life prediction of food items. The system generates a data model using a knowledge graph indicative of a hierarchical taxonomy for a plurality of categories of the plurality of food items, which in turn contains metadata representing similarities in physio-chemical degradation pattern of different classes of the food items. This data model serves as a generic data model for real-time shelf-life prediction of different food items.

Abstract: A computer-implemented method for defect analysis is provided. The computer-implemented method includes obtaining a plurality of sets of defect point coordinates, a respective set of the plurality of sets of detect point coordinates including coordinates of defect points in a respective substrate of a plurality of substrates, the coordinates of defect points in the respective substrate being coordinates in an image coordinate system; combining the plurality of sets of defect point coordinates according to the image coordinate system into a composite set of coordinates to generate a composite image; and performing a clustering analysis to classify defect points in the composite set in the composite image into a plurality of clusters.

Abstract: This disclosure presents a process to determine an alignment parameter for geosteering a wellbore undergoing drilling operations. The process can receive one or more azimuthal image log data sets, one or more geology logs, and other input parameters. The image log data sets can be transformed to better approximate the geology logs, such as transforming a 3D representation to a 2D representation and flattening out curves represented in the original image log data. The geology logs or transformed image log data can then be moved to create an approximate alignment between the other log data. The movement, which can be a sliding movement, a linear movement, a tilting movement, an angling movement, or a rotating movement, can be used to determine the determined alignment parameter or final alignment parameter. The alignment parameter can be used as input into a geosteering system for the wellbore.

Abstract: A method for assessing cardiothoracic ratio (CTR) includes following steps. A testing X-ray image database of a subject is provided. A first image data classifying step is performed, wherein the testing X-ray image database is classified by a first deep learning neural network classifier to obtain a testing chest X-ray image data. A second image data classifying step is performed, wherein the testing chest X-ray image data is classified by a second deep learning neural network classifier to obtain a target chest X-ray image data. A feature extracting step is performed, wherein a diameter of thoracic cavity and a diameter of cardiac silhouette of the target chest X-ray image data are captured automatically and then trained to achieve a convergence by a third deep learning neural network classifier. An assessing step is performed, wherein an assessing result of CTR is obtained according to a feature of CTR.

Abstract: A method of generating a segmentation confidence map by processing classification values each indicating a respective classification of a respective voxel of a retinal C-scan into a respective retinal layer class of a predefined set of retinal layer classes, the method comprising: generating, for each voxel, a respective confidence value which indicates a level of confidence in the classification of the voxel; for a retinal layer class of the predefined set, identifying a subset of the voxels such that the classification value generated for each voxel indicates a classification of the voxel into the retinal layer class; calculating, for each A-scan having voxels in the identified subset, a respective average of the confidence indicator values generated for the voxels; and using the calculated averages to generate the map, which indicates a spatial distribution of a level of confidence in the classification of the voxels.

Abstract: Various embodiments of the present disclosure provide for accelerated segmentation for reverse engineering of integrated circuits. In one example, an embodiment provides for receiving an SEM image for an integrated circuit, performing filtering and binarization with respect to the SEM image, extracting information associated with filter sizes for the filtering, extracting signatures related to a distribution for background pixels and foreground pixels of the SEM image, extracting respective distance to mean signatures for the background pixels and the foreground pixels, and segmenting the SEM image based at least in part on the filter sizes and the respective distance to mean signatures to generate a segmented image for the integrated circuit.