Abstract: An image processing device (100) includes an object detecting unit (103a) that detects objects each appearing in a corresponding one of pieces of image data; an object tracking unit (103b) that tracks the detected objects in a time direction; a descriptor generating unit (104) that generates feature descriptors of the respective objects on the basis of results of the detection and results of the tracking of the objects; a data recording control unit (105) that forms a database from the generated feature descriptors and the pieces of image data of the objects corresponding to the feature descriptors; an image retrieving unit (108a) that retrieves, from the database, object groups that match a retrieval condition and form a pair of object groups appearing in pieces of image data obtained by capturing different regions, each of the object groups corresponding to a corresponding one of the regions; a feature extracting unit (108b) that extracts a feature to be used for checking, from pieces of image data and feat

Abstract: Specification covers new algorithms, methods, and systems for: Artificial Intelligence; the first application of General-AI. (versus Specific, Vertical, or Narrow-AI) (as humans can do) (which also includes Explainable-AI or XAI); addition of reasoning, inference, and cognitive layers/engines to learning module/engine/layer; soft computing; Information Principle; Stratification; Incremental Enlargement Principle; deep-level/detailed recognition, e.g., image recognition (e.g., for action, gesture, emotion, expression, biometrics, fingerprint, tilted or partial-face, OCR, relationship, position, pattern, and object); Big Data analytics; machine learning; crowd-sourcing; classification; clustering; SVM; similarity measures; Enhanced Boltzmann Machines; Enhanced Convolutional Neural Networks; optimization; search engine; ranking; semantic web; context analysis; question-answering system; soft, fuzzy, or un-sharp boundaries/impreciseness/ambiguities/fuzziness in class or set, e.g.

Abstract: A face recognition method includes capturing a background of an image; after determining that a face exists in the image, determining a face region of interest (ROI) of the face; capturing a foreground of the image with the face; and comparing the face ROI and the foreground of the image to determine whether the face is authentic or not.

Abstract: Systems and methods for assessing a physical structure are provided. Information indicative of an infrared image that includes a portion of the physical structure is received, and one or more indicators within the infrared image exceeding a heat threshold are determined. A plurality of characteristics of the one or more indicators are determined. One or more edges of the portion of the physical structure are detected, and an area associated with an intended use of one or more fasteners associated with the physical structure is determined according to the detected edges. An amount of the one or more indicators corresponding to the area is determined, and the one or more indicators are classified as fasteners according to the determined amount. Based on the classification of the one or more indicators, a condition of the physical structure is determined.

Abstract: Embodiments can provide a computer implemented method in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to cause the processor to implement a system for providing profile photo enhancement, the method comprising receiving, from a specification source, one or more specifications for image acceptance criteria; receiving, from an uploading user, an image; examining, through an image processing toolbox, the image to determine if all of the image acceptance criteria are met; if all image acceptance criteria are met, accepting the image; and if one or more image acceptance criteria are not met, processing the image.

Abstract: Concepts and technologies directed to surrogate metadata aggregation for dynamic content assembly are disclosed. Embodiments can include a system that comprises a processor and a memory that stores computer-executable instructions that configure a processor to perform operations. The operations can include obtaining a first visual content from a digital data store, where the first visual content is configured to digitally represent a first scene. The operations can include performing image recognition on the first visual content so as to identify a second visual content that is digitally configured to represent a second scene. The operations can include determining that native original metadata cannot be obtained for the first visual content, where the native original metadata includes information about the first scene digitally represented by the first visual content.

Abstract: A system for aerial image detection and classification is provided herein. The system comprising an aerial image database storing one or more aerial images electronically received from one or more image providers, and an object detection pre-processing engine in electronic communication with the aerial image database, the object detection pre-processing engine detecting and classifying objects using a disparity mapping generation sub-process to automatically process the one or more aerial images to generate a disparity map providing elevation information, a segmentation sub-process to automatically apply a pre-defined elevation threshold to the disparity map, the pre-defined elevation threshold adjustable by a user, and a classification sub-process to automatically detect and classify objects in the one or more stereoscopic pairs of aerial images by applying one or more automated detectors based on classification parameters and the pre-defined elevation threshold.

Abstract: A method of monitoring or analyzing a manufacturing of a semiconductor structure includes providing a semiconductor structure; providing a camera disposed around the semiconductor structure; disposing a liquid substance over the semiconductor structure; removing a portion of the semiconductor structure; removing the liquid substance from the semiconductor structure; capturing a plurality of first images of the semiconductor structure by the camera; analyzing the plurality of first images; identifying a region of the semiconductor structure where a residue of the liquid substance is disposed based on the analysis of the plurality of first images; and performing a response based on the identification of the region of the semiconductor structure.

Abstract: Embodiments include a system, method, and computer program product for distributed intelligent pattern recognition. Embodiments include a cooperative multi-agent detection system that enables an array of disjunctive devices (e.g., cameras, sensors) to selectively cooperate to identify objects of interest over time and space, and to contribute an object of interest to a shared deep learning pattern recognition system based on a bidirectional feedback mechanism. Embodiments provide updated information and/or algorithms to one or more agencies for local system learning and pattern updating recognition models. Each of the multiple agencies may in turn, update devices (e.g., cameras, sensors) coupled to the local machine learning and pattern recognition models.

Abstract: A target including a reference object of a known size is prepared. The reference object from target image data, which is generated by photographing the target using a survey instrument, is detected through image processing to calculate first size data on dimensions of the reference object. A defect from external appearance image data, which is generated by photographing an external appearance of a structure using the survey instrument, is detected through image processing to calculate defect data on dimensions of the defect. The first size data is compared with second size data on actual dimensions of the reference object to calculate correction data, which is used to correct the defect data.

Abstract: Various embodiments of a cyber-physical system for providing cloud prediction for photovoltaic array control are disclosed herein.

Abstract: A disparity determining method, an electronic device, and a computer-readable storage medium are provided. The disparity determining method includes: downsampling a first image and a second image, to obtain a first image with a first size and a second image with the first size; performing first-stage disparity computation on the first image with the first size and the second image with the first size, to obtain a first disparity map with the first size; and performing second-stage disparity computation on a first image with a second size and a second image with the second size based on an upsampled disparity map, with the second size, of the first disparity map, to obtain a second disparity map with the second size.

Abstract: A determination device that determines quality of target portion based on sensor data obtained by a sensor measuring the target object, includes one or more processors configured to acquire sensor data representing the target portion, acquire information indicating a changed portion, determine whether the target portion includes the changed portion based on acquired information, determine a first label of the target portion represented in the sensor data by using a determination model learned from a training dataset based on training target portions, the first label representing target portion as one of good, defect, and a defect candidate, accept a second label of the target portion input via a user interface when the target portion includes the changed portion or when the first label of the target portion is determined as the defect candidate, and perform quality determination of the target portion based on the first label and/or the second label.

Abstract: A computer-implemented method and systems are provided for performing machine learning for an image classification task. The method includes overlaying, by a processor operatively coupled to one or more databases, a second image on a first image obtained from one or more training sets in the one or more databases, to form a mixed image, by averaging an intensity of each of a plurality of co-located pixel pairs in the first and the second image. The method also includes training, by the processor, a machine learning process configured for the image classification task using the mixed image to augment data used by the machine learning process for the image classification task.

Abstract: A detecting method and a detecting device for a display panel are provided. The detecting method includes: collecting a first detection image of the display panel, and acquiring a gray scale value of each of pixel elements in the first detection image; determining the pixel element of the first detection image having the gray scale value outside a default gray scale range as a first pixel element, determining a first communication region constituted by each of the first pixel element of the first detection image, and calculating an aspect ratio of the first communication region; and looking up a target parameter matching with the aspect ratio of the first communication region from a pre-built database, and determining a target type corresponding to the target parameter as a type of the display panel.

Abstract: A system and method is provided for displaying surfaces of an object from a vantage point different from the vantage point from which imagery of the object was captured. In some aspects, imagery may be generated for display by combining visual characteristics from multiple source images and applying greater weight to the visual characteristics of some of the source images relative to the other source images. The weight may be based on the orientation of the surface relative to the location from which the image was captured and the location from which the object will be displayed.

Abstract: An automatic optical inspection device, including an image storage unit; an image computing unit; and an image acquisition unit. The image storage unit includes a first communication interface and a second communication interface. The image computing unit includes a first optical interface, a second optical interface, a third optical interface, and a fourth optical interface; the image acquisition unit includes a third communication interface and a camera interface. The image storage unit is configured to transmit configuration parameters and test commands to the image computing unit, receive a test result transmitted from the image computing unit via the first communication interface, and receive data from the image acquisition unit via the second communication interface. The image computing unit is configured to receive the configuration parameters and test commands from the image storage unit, and transmit the test result to the image storage unit via the first fiber interface.

Abstract: There is provided a method and apparatus for segmenting two-dimensional images of an anatomical structure. A time sequence of two-dimensional images of the anatomical structure is acquired (202) and a segmentation model for the anatomical structure is acquired (204). The segmentation model comprises a plurality of segments. The acquired segmentation model is applied to the entire time sequence of two-dimensional images of the anatomical structure simultaneously in time and space to segment the time sequence of two-dimensional images by way of the plurality of segments (206).

Abstract: A depth calculation processor, a data processing method, and a 3D image device are disclosed herein. The depth calculation processor includes: two input ports to receive a first image data, wherein the first image data comprises structured light image acquired under projection of structured light; an input switch connected to the input ports and to convey all or some of the first image data from the input ports; a data processing engine connected to the input switch and to process the first image data that is output through the input switch and to output a second image data, wherein the second image data comprises a depth map, wherein the data processing engine comprises a depth processing engine to process the structured light image to obtain the depth map; and one output port connected to the data processing engine and to output the second image data to a main device.

Abstract: A method for creating a digital 3D representation of a physical object, the physical object comprising an object surface; wherein the method comprises: obtaining input data, the input data including a plurality of captured images of the physical object and surface normal information of the object, the captured images being captured by an image capturing device, the surface normal information representing object surface normals associated with respective parts of the object surface; creating a digital 3D representation of the object surface; wherein creating the digital 3D representation is based on at least the obtained plurality of captured images and the obtained surface normal information.