Shape And Form Analysis Patents (Class 382/203)
  • Patent number: 11443416
    Abstract: Various embodiments are generally directed to techniques for image content extraction. Some embodiments include extracting contextually structured data from document images, such as by automatically identifying document layout, document data, document metadata, and/or correlations therebetween in a document image, for instance. Several embodiments include extracting contextually structured data from table images, such as gridded and non-gridded tables. For example, the contents of cells may be extracted from a table image along with structural context including the corresponding row and column information. Many embodiments are directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. Several embodiments are directed to automatically identifying and associating document metadata with corresponding document data in a document image to generate a machine-facilitated annotation of the document image.
    Type: Grant
    Filed: August 9, 2021
    Date of Patent: September 13, 2022
    Assignee: SAS INSTITUTE INC.
    Inventors: Yi Liao, Charles Franklin Board, William Robert Nadolski, David James Wheaton, Heather Michelle Goodykoontz, Adheesha Sanjuaya Arangala, Karthik Nakkeeran
  • Patent number: 11417129
    Abstract: According to one embodiment, an image analysis device includes one or more processors configured to receive input of an image; calculate feature amount information indicating a feature of a region of the image; recognize a known object from the image on the basis of the feature amount information, the known object being registered in learning data of image recognition; recognize a generalization object from the image on the basis of the feature amount information, the generalization object being generalizable from the known object; and output output information on an object identified from the image as the known object or the generalization object.
    Type: Grant
    Filed: February 26, 2019
    Date of Patent: August 16, 2022
    Assignee: KABUSHIKI KAISHA TOSHIBA
    Inventors: Quoc Viet Pham, Tatsuo Kozakaya
  • Patent number: 11396099
    Abstract: Various embodiments for enforcing safe operation of machinery performing an activity in a three-dimensional (3D) workspace includes computationally generating a 3D spatial representation of the workspace; computationally mapping 3D regions of the workspace corresponding to space occupied by the machinery and a human; and based thereon, restricting operation of the machinery in accordance with a safety protocol during physical performance of the activity.
    Type: Grant
    Filed: August 21, 2020
    Date of Patent: July 26, 2022
    Assignee: Veo Robotics, Inc.
    Inventors: Marek Wartenberg, Paul Jakob Schroeder, Brad C. Mello, Clara Vu, Scott Denenberg, Nicole Aucoin, Alberto Moel
  • Patent number: 11351810
    Abstract: The present invention proposes a method for producing an authenticable moiré shape that simultaneously moves and shows a beating effect. The method relies on a combination of the 1D or the 2D moiré and the level line moiré. When tilting a compound showing such a moiré, the moiré shape moves, its intensity levels change significantly but its shape remains the same and is recognizable. Embodiments comprise a base layer made of patterned metallic tiny shapes and a revealing layer made of a 1D array of cylindrical lenslets or of a 2D array of spherical or aspherical lenslets.
    Type: Grant
    Filed: September 10, 2020
    Date of Patent: June 7, 2022
    Assignee: Ecole Polytechnique Fédérale de Lausanne (EPFL)
    Inventors: Thomas Walger, Roger D. Hersch, Jürgen Brugger
  • Patent number: 11345036
    Abstract: A robot control device is configured to control a robot operating in a shared work area with an operator. The robot control device includes a distance estimation unit configured to obtain a reachable range of the operator on the basis of information on position and information on physical characteristics of the operator, and obtain a distance between the reachable range and the robot on the basis of information on position and information on shape of the robot and the reachable range, an interference probability calculation unit configured to obtain an interference probability between the robot and the operator on the basis of the distance, and an operation control unit configured to control operation of the robot on the basis of the interference probability.
    Type: Grant
    Filed: October 29, 2019
    Date of Patent: May 31, 2022
    Assignee: FANUC CORPORATION
    Inventor: Masahiro Ueno
  • Patent number: 11338102
    Abstract: A method of determining facial metrics of a patient includes: capturing a first image of the patient with an image capturing device positioned in a first known position with the assistance of a positioning device, capturing a second image of the patient with the image capturing device positioned in a second known position different that the first known position with the assistance of the positioning device, and determining facial metrics of the patient by analyzing the first image and the second image.
    Type: Grant
    Filed: December 14, 2018
    Date of Patent: May 24, 2022
    Assignee: Koninklijke Philips N.V.
    Inventors: Peter Chi Fai Ho, Richard Thomas Haibach, Daniel Steed, Robert William Baiko
  • Patent number: 11301725
    Abstract: The present invention discloses a visual relationship detection method based on a region-aware learning mechanism, comprising: acquiring a triplet graph structure and combining features after its aggregation with neighboring nodes, using the features as nodes in a second graph structure, and connecting in accordance with equiprobable edges to form the second graph structure; combining node features of the second graph structure with features of corresponding entity object nodes in the triplet, using the combined features as a visual attention mechanism and merging internal region visual features extracted by two entity objects, and using the merged region visual features as visual features to be used in the next message propagation by corresponding entity object nodes in the triplet; and after a certain number of times of message propagations, combining the output triplet node features and the node features of the second graph structure to infer predicates between object sets.
    Type: Grant
    Filed: August 31, 2020
    Date of Patent: April 12, 2022
    Assignee: TIANJIN UNIVERSITY
    Inventors: Anan Liu, Hongshuo Tian, Ning Xu, Weizhi Nie, Dan Song
  • Patent number: 11275963
    Abstract: An image identification apparatus includes: a memory; and a processor coupled to the memory, the processor being configured to perform processing, the processing including: acquiring a contour image where pixels indicating a contour of a subject are extracted from an input image; detecting pixels of 3 points or more over the contour from each of regions in the contour image, which are separated by a predetermined distance in a vertical direction or a horizontal direction; calculating, for each combination of pixels of every 2 points among the detected pixels, an intersection point of a perpendicular bisector of a line segment having 2 points as end points and a distance between the intersection point and one of the detected pixels; and identifying, from the input image, a circle having the intersection point as a center of the circle and the distance as a radius.
    Type: Grant
    Filed: November 5, 2020
    Date of Patent: March 15, 2022
    Assignee: FUJITSU LIMITED
    Inventor: Fang Yin
  • Patent number: 11263192
    Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises generating a context data tree for each variable in a plurality of variables based on a received input; determining data folding points for each generated context data tree; conducting a hyper-folding process on the determined data folding points in each context data tree, wherein the hyper-folding process converts each generated context data tree into a single data tree; and automatically loading the single data tree into an application.
    Type: Grant
    Filed: November 18, 2019
    Date of Patent: March 1, 2022
    Assignee: International Business Machines Corporation
    Inventors: Chiwen Chang, Hsiang Chang, Ming Jyh Hsieh
  • Patent number: 11244200
    Abstract: An image processing method that includes setting a plurality of search areas of a predetermined size having mutually different circumferential positions along a peripheral edge part and extending in a radial direction from a center of a recess toward the peripheral edge part near the peripheral edge part in an image, executing an edge detection in each search area to obtain detected edge position and edge intensity for each search area, obtaining a relative shift amount for making a degree of similarity of image patterns highest for each search area when another search area adjacent to the search area in the circumferential direction is shifted in the radial direction with respect to the search area, and specifying a position of the boundary in one search area based on the edge positions, the edge intensities and the relative shift amounts in the search area and each of the search areas in neighboring ranges in the circumferential direction.
    Type: Grant
    Filed: December 21, 2018
    Date of Patent: February 8, 2022
    Inventor: Takuya Yasuda
  • Patent number: 11238269
    Abstract: There is provided an encoding and decoding method and an information recognition device using the same. A code block includes a center coding region and a peripheral coding region arranged around the center coding region. The encoding and decoding method uses the feature of at least one microdot included in the center coding region as codes. The encoding and decoding method uses the feature of at least one microdot included in the peripheral coding region as codes. The encoding and decoding method uses the relative feature between the center coding region and the peripheral coding region as codes. The information recognition device compares the read feature with pre-stored features to decode information such as position codes, object codes, parameter codes and control codes.
    Type: Grant
    Filed: September 7, 2020
    Date of Patent: February 1, 2022
    Assignee: PIXART IMAGING INC.
    Inventors: En-Feng Hsu, Shu-Sian Yang, Yi-Hsien Ko
  • Patent number: 11233933
    Abstract: A method for processing an image is provided. The method includes that: a preview image to be processed is acquired; scene information is identified from the preview image; a composition mode corresponding to the scene information is determined; and the preview image is composed according to the composition mode. A device for processing an image and a mobile terminal are also provided.
    Type: Grant
    Filed: July 9, 2019
    Date of Patent: January 25, 2022
    Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.
    Inventor: Yaoyong Liu
  • Patent number: 11210793
    Abstract: In general, embodiments of the present invention provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for performing mixed reality processing using at least one of depth-based partitioning of a point cloud capture data object, object-based partitioning of a point cloud capture data object, mapping a partitioned point cloud capture data object to detected objects of a three-dimensional scan data object, performing noise filtering on point cloud capture data objects based at least in part on geometric inferences from three-dimensional scan data objects, and performing geometrically-aware object detection using point cloud capture data objects based at least in part on geometric inferences from three-dimensional scan data objects.
    Type: Grant
    Filed: February 12, 2021
    Date of Patent: December 28, 2021
    Assignee: Optum Technology, Inc.
    Inventors: Yash Sharma, Vivek R. Dwivedi, Anshul Verma
  • Patent number: 11170512
    Abstract: An image processing apparatus for extracting features from video frames of a video; and determining, for non-initial video frames, reference information of an object detected in a previous video frame thereof in a corresponding non-initial video frame with respect to object information of the object; and detecting an object from an initial video frame based on the features and detects an object from non-initial video frames based on the features and the determined reference information. The processing time of the object detection processing can be reduced, and the real-time requirements of object detection in the video can be better satisfied.
    Type: Grant
    Filed: January 3, 2020
    Date of Patent: November 9, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventors: Zhiyuan Zhang, Yaohai Huang, Deyu Wang
  • Patent number: 11113571
    Abstract: A computer-implemented method for target object position prediction includes receiving, via an RGB camera a plurality of images depicting one or more persons positioned on a floor. A plurality of person location labels is assigned to each image indicating where the one or more persons are located relative to the floor. A foot position (FP) classifier is trained to classify the images into the person location labels, wherein the FP classifier is configured according to a multi-layer architecture and the training results in determination of a plurality of weights for connecting layers in the multi-layer architecture. A deployment of the FP classifier is created based on the multi-layer architecture, the plurality of weights, and the plurality of person location labels.
    Type: Grant
    Filed: October 11, 2019
    Date of Patent: September 7, 2021
    Assignee: Kognition LLC
    Inventors: James Carroll, Michael Grinshpon
  • Patent number: 11113517
    Abstract: An ink parsing system receives ink strokes at an inking device input and render the received ink strokes into an image in a pixel space. Writing strokes are detected in the image and labeled. Pixels corresponding to the labeled writing strokes are removed from the image. Drawing strokes in the image having the removed pixels are detected using and labeled. Writing objects and drawing objects corresponding, respectively, to the labeled writing strokes and the labeled drawing strokes are output. A digital ink parsing pipeline is thereby provided having accurate ink stroke detection and segmentation.
    Type: Grant
    Filed: March 20, 2019
    Date of Patent: September 7, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Yixin Shi, Aman Orazaev, Tianyi Chen, Sheng Yi
  • Patent number: 11093758
    Abstract: An information processing system S includes a server device, and an information processing device communicable with the server device. The information processing device is configured to acquire a plurality of images imaged by an imaging device included in a vehicle, and output to the server device, when detecting a change from a non-rainfall state to a rainfall state, or a change from the rainfall state to the non-rainfall state based on the acquired images, location information regarding the vehicle when the change is detected.
    Type: Grant
    Filed: October 8, 2019
    Date of Patent: August 17, 2021
    Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
    Inventors: Hideo Hasegawa, Keiko Kameda, Misa Ejiri, Shintaro Naruse, Tadahiro Kashiwai, Naoya Oka, Kensuke Koike, Hiroyuki Monji
  • Patent number: 11080812
    Abstract: An image recognition apparatus includes a processor including a plurality of arithmetic units; and a memory storing a plurality of data elements, each corresponding to one of candidate regions detected in an image and indicating a location and an evaluation value of the corresponding candidate region. The processor sorts the data elements by calculating in parallel, in reference to evaluation values, indexes each indicating a position of a corresponding one of the data elements in a sorted ordering and transferring in parallel, after the calculation of the indexes, the data elements based on the indexes. The processor selects part of the candidate regions based on the sorted ordering of the data elements.
    Type: Grant
    Filed: August 19, 2019
    Date of Patent: August 3, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Takuya Fukagai, Kyosuke Maeda, Koichi Shirahata, Yasumoto Tomita
  • Patent number: 11068493
    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for guided visual search. A visual search query can be represented as a sketch sequence that includes ordering information of the constituent strokes in the sketch. The visual search query can be encoded into a structural search encoding in a common search space by a structural neural network. Indexed visual search results can be identified in the common search space and clustered in an auxiliary semantic space. Sketch suggestions can be identified from a plurality of indexed sketches in the common search space. A sketch suggestion can be identified for each semantic cluster of visual search results and presented with the cluster to guide a user towards relevant content through an iterative search process. Selecting a sketch suggestion as a target sketch can automatically transform the visual search query to the target sketch via adversarial images.
    Type: Grant
    Filed: November 7, 2018
    Date of Patent: July 20, 2021
    Assignee: Adobe Inc.
    Inventors: Hailin Jin, John Collomosse
  • Patent number: 11070501
    Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. A novel, computerized framework for automatically identifying and recommending socially-engaging photos to their creators for sharing is provided. Execution of the disclosed framework turns a tedious manual chore into an automated, software-driven process.
    Type: Grant
    Filed: January 31, 2017
    Date of Patent: July 20, 2021
    Assignee: VERIZON MEDIA INC.
    Inventors: Yoelle Maarek, Ido Guy, Dan Pelleg, Idan Szpektor, Alexander Nus, Jeffrey Bonforte
  • Patent number: 11062169
    Abstract: Apparatus, methods and systems of object recognition are disclosed. Embodiments of the inventive subject matter generates map-altered image data according to an object-specific metric map, derives a metric-based descriptor set by executing an image analysis algorithm on the map-altered image data, and retrieves digital content associated with a target object as a function of the metric-based descriptor set.
    Type: Grant
    Filed: July 8, 2019
    Date of Patent: July 13, 2021
    Assignee: Nant Holdings IP, LLC
    Inventor: Matheen Siddiqui
  • Patent number: 11049275
    Abstract: A method and apparatus for outputting three-dimensional (3D) lines. The apparatus acquires a first image and a second image including lines on a road, generates, based on a first feature map acquired from the first image, a line probability map representing a probability that a pixel point of the first feature map belongs to the lines, calculates matching information of the first image and the second image based on the first feature map and a second feature map acquired from the second image, predicts depth values of the lines using the line probability map and the matching information, detects the lines based on the line probability map, generates 3D lines based on the detected lines and the depth values of the lines, and outputs the 3D lines.
    Type: Grant
    Filed: August 26, 2019
    Date of Patent: June 29, 2021
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Zhihua Liu, Leewon Hee, Lin Ma, Qiang Wang, Tianhao Gao, Yamin Mao
  • Patent number: 11011004
    Abstract: A server collects measurement data of a camera to efficiently generate statistical data relating to the number of entering and exiting persons, and present the data to a user.
    Type: Grant
    Filed: November 7, 2017
    Date of Patent: May 18, 2021
    Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
    Inventors: Masashi Oozono, Kazuhiko Iwai
  • Patent number: 11010543
    Abstract: Computerized systems and methods for identifying a table in a document include: removing from a document content other than text characters and associated size, position and format information; converting each text character into a block covering the corresponding text character; converting each page of the document into a corresponding image file; drawing a set of horizontal lines spanning a width of the document, each block super-scored and under-scored by at least one of the horizontal lines; drawing a set of vertical lines spanning all or a portion of a length of the document; removing a subset of redundant vertical lines; and determining, based on the set of horizontal lines and the subset of vertical lines, (i) a set of table coordinates corresponding to a table in the document, and (ii) one or more sets of cell coordinates corresponding to one or more cells in the table.
    Type: Grant
    Filed: August 11, 2020
    Date of Patent: May 18, 2021
    Assignee: FMR LLC
    Inventors: Aishwarya Vijay Wesanekar, Subramaniam Vaithiyalingam, Deepak Venkatachalapathi, Seth Warren Brooks, Biju Kozhikode Kizhakhemadtil
  • Patent number: 10998007
    Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that can generate a context-aware-video-progress bar including a video-scene-proportionate timeline with time-interval sections sized according to relative scene proportions within time intervals of a video. In some implementations, for instance, the disclosed systems determine relative proportions of scenes within a video across time intervals of the video and generate a video-scene-proportionate timeline comprising time-interval sections sized proportionate to the relative proportions of scenes across the time intervals. By integrating the video-scene-proportionate timeline within a video-progress bar, the disclosed systems generate a context-aware-video-progress bar for a video.
    Type: Grant
    Filed: September 30, 2019
    Date of Patent: May 4, 2021
    Assignee: ADOBE INC.
    Inventors: Ajay Bedi, Amol Jindal
  • Patent number: 10990881
    Abstract: Systems and methods are described herein. In one embodiment, the method includes receiving a goal associated with a predicate-object pair; receiving utilization data including a plurality of predicate-object pairs including the predicate-object pair associated with the goal; determining a prediction model comprising a plurality of nodes that form a hierarchical structure including a root node and two or more leaf nodes and organized based on one or more of an information gain and a business gain, the two or more leaf nodes including a leaf node associated with the predicate-object pair of the goal; identifying nodes in the hierarchical structure that trace a path from the root node to the node associated with the goal; and causing a recommendation for at least partial completion of the goal to be presented to a user, the recommendation based on the one or more nodes that trace the path.
    Type: Grant
    Filed: August 25, 2015
    Date of Patent: April 27, 2021
    Assignee: Progress Software Corporation
    Inventors: Ivan Osmak, Thomas Krüger
  • Patent number: 10963506
    Abstract: The technology disclosed relates to neural network-based systems and methods of preparing a data object creation and recommendation database.
    Type: Grant
    Filed: November 14, 2017
    Date of Patent: March 30, 2021
    Assignee: Evolv Technology Solutions, Inc.
    Inventors: Myles Brundage, Risto Miikkulainen
  • Patent number: 10956790
    Abstract: A graphical user interface comprising a data interface for receiving a set of text documents; a calculator for transforming each received text document into a vector of a n-dimensional manifold, n being larger than 2; transforming each n-dimensional manifold vector into a 2-D data; generating a first mapping of what 2-D data corresponds to what n-dimensional manifold vector; and generating a second mapping of what 2-D data corresponds to what received text document; a first user display arranged for displaying each 2-D data on a 2-D plane; a first user interface arranged for allowing a user to select a subset of the displayed 2-D data; wherein selecting said subset of 2-D data automatically selects the n-dimensional manifold vectors that correspond to said subset of 2-D data; and a second user display arranged for displaying a list of the text documents that correspond to said subset of 2-D data.
    Type: Grant
    Filed: May 24, 2019
    Date of Patent: March 23, 2021
    Assignee: INDICO
    Inventors: Slater Victoroff, Madison May
  • Patent number: 10922353
    Abstract: A system and method for determining an object or product represented in an image is disclosed. The system receives a first image, determines a region of interest in the first image, determines a classification score for the region of interest using a convolutional neural network that assigns the region of interest the classification score corresponding to a class, and identifies a first product in the first image based on the classification score.
    Type: Grant
    Filed: February 1, 2019
    Date of Patent: February 16, 2021
    Assignee: Ricoh Company, Ltd.
    Inventors: Junghyun Kwon, Ramya Narasimha, Edward L. Schwartz, Max McFarland, Silvio Savarese, Kathrin Berkner
  • Patent number: 10909711
    Abstract: A method of determining a pose of an image capture device includes capturing an image using an image capture device. The method also includes generating a data structure corresponding to the captured image. The method further includes comparing the data structure with a plurality of known data structures to identify a most similar known data structure. Moreover, the method includes reading metadata corresponding to the most similar known data structure to determine a pose of the image capture device.
    Type: Grant
    Filed: December 5, 2016
    Date of Patent: February 2, 2021
    Assignee: Magic Leap, Inc.
    Inventors: Brigit Schroeder, Tomasz J. Malisiewicz, Andrew Rabinovich
  • Patent number: 10904476
    Abstract: Techniques for automated up-sampling of media files are provided. In some examples, a title associated with a media file, a metadata file associated with the title, and the media file may be received. The media file may be partitioned into one or more scene files, each scene file including a plurality of frame images in a sequence. One or more up-sampled scene files may be generated, each corresponding to a scene file of the one or more scene files. An up-sampled media file may be generated by combining at least a subset of the one or more up-sampled scene files. Generating one or more up-sampled scene files may include identifying one or more characters in a frame image of the plurality of frame images, based at least in part on implementation of a facial recognition algorithm including deep learning features in a neural network.
    Type: Grant
    Filed: December 12, 2019
    Date of Patent: January 26, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Christian Garcia Siagian, Charles Effinger, David Niu, Yang Yu, Narayan Sundaram, Arjun Cholkar, Ramakanth Mudumba
  • Patent number: 10872405
    Abstract: A system for creating component shape data for image processing to be used when performing image recognition of a component to be mounted by a component mounter, the system including: a display section; a wire frame drawing section configured to draw a wire frame on top of the component image, and to move a position of a side of the wide frame in accordance with a drag operation of an operator; a minimum unit specifying section configured to specify a minimum unit for when measuring the shape data of the measurement target portion surrounded by the wire frame; and a component shape data creation section configured to create the component shape data for image processing by measuring with an accuracy using the minimum unit specified by the minimum unit specifying section for the shape data of the measurement target portion surrounded by the wire frame.
    Type: Grant
    Filed: November 1, 2016
    Date of Patent: December 22, 2020
    Assignee: FUJI CORPORATION
    Inventors: Hiroshi Oike, Shuichiro Kito, Kenji Sugiyama
  • Patent number: 10860683
    Abstract: The general problem of pattern change discovery between high-dimensional data sets is addressed by considering the notion of the principal angles between the subspaces is introduced to measure the subspace difference between two high-dimensional data sets. Current methods either mainly focus on magnitude change detection of low-dimensional data sets or are under supervised frameworks. Principal angles bear a property to isolate subspace change from the magnitude change. To address the challenge of directly computing the principal angles, matrix factorization is used to serve as a statistical framework and develop the principle of the dominant subspace mapping to transfer the principal angle based detection to a matrix factorization problem. Matrix factorization can be naturally embedded into the likelihood ratio test based on the linear models. The method may be unsupervised and addresses the statistical significance of the pattern changes between high-dimensional data sets.
    Type: Grant
    Filed: October 23, 2013
    Date of Patent: December 8, 2020
    Assignee: The Research Foundation for The State University of New York
    Inventors: Yi Xu, Zhongfei Mark Zhang
  • Patent number: 10855933
    Abstract: A terminal according to the present disclosure comprises an inputter for receiving input of a preview image converted from light reflected from surroundings of the terminal; a controller for identifying a type of an object included in the preview image and selecting two or more image filters using a recommended algorithm regarding an image filter to be applied to the preview image; and a display for displaying the preview image to which the selected two or more image filters are applied, wherein the controller may apply a first image filter of the two or more filters to a first image area of the preview image and apply a second image filter that is different from the first image filter to a second image area that is an area excluding the first image area of the preview image.
    Type: Grant
    Filed: January 28, 2019
    Date of Patent: December 1, 2020
    Assignee: HYPERCONNECT, INC.
    Inventors: Sangil Ahn, Beomjun Shin, Minsik Oh, Eunhee Choi
  • Patent number: 10805527
    Abstract: An image processing device includes: a communication interface configured to receive an original image from a camera; a processor configured to determine a mask area of the original image, extract a switched point among a series of pixels in the mask area, and switch, on the basis of the switched point, a first pixel value of a first pixel set and a second pixel value of a second pixel set and generate a masked image; and a memory storing the masked image and information about the switched point, wherein the switched point is one or more, and the series of pixels sequentially include the first pixel set and the second pixel set.
    Type: Grant
    Filed: December 29, 2016
    Date of Patent: October 13, 2020
    Assignee: HANWHA TECHWIN CO., LTD.
    Inventor: Sun Ae Park
  • Patent number: 10789697
    Abstract: Devices, systems, and methods obtain respective corresponding feature-detection scores for a plurality of areas in an image; calculate respective corresponding sorting scores for at least some areas of the plurality of areas; for the at least some areas of the plurality of areas, arrange the corresponding feature-detection scores in order of the corresponding sorting scores, thereby generating an order of sorted feature-detection scores; and assign respective detection scores to the at least some areas based on the order of sorted feature-detection scores and on three or more of the following: the respective corresponding feature-detection scores of the areas, a spectral threshold, a spatial threshold, and a neighborhood kernel.
    Type: Grant
    Filed: February 22, 2019
    Date of Patent: September 29, 2020
    Assignee: Canon Virginia, Inc.
    Inventors: Nikhil Krishnan, Bradley Scott Denney
  • Patent number: 10769776
    Abstract: A system and method for scoring trained probes for use in analyzing one or more candidate poses of a runtime image is provided. A set of probes with location and gradient direction based on a trained model are applied to one or more candidate poses based upon a runtime image. The applied probes each respectively include a discrete set of position offsets with respect to the gradient direction thereof. A match score is computed for each of the probes, which includes estimating a best match position for each of the probes respectively relative to one of the offsets thereof, and generating a set of individual probe scores for each of the probes, respectively at the estimated best match position.
    Type: Grant
    Filed: February 10, 2017
    Date of Patent: September 8, 2020
    Assignee: Cognex Corporation
    Inventor: Nathaniel R. Bogan
  • Patent number: 10767981
    Abstract: Systems and methods in accordance with embodiments of the invention estimate depth from projected texture using camera arrays. One embodiment of the invention includes: at least one two-dimensional array of cameras comprising a plurality of cameras; an illumination system configured to illuminate a scene with a projected texture; a processor; and memory containing an image processing pipeline application and an illumination system controller application. In addition, the illumination system controller application directs the processor to control the illumination system to illuminate a scene with a projected texture.
    Type: Grant
    Filed: October 31, 2018
    Date of Patent: September 8, 2020
    Assignee: FotoNation Limited
    Inventors: Kartik Venkataraman, Jacques Duparré
  • Patent number: 10755132
    Abstract: A method for extracting a surface deformation feature of an object based on linear scanning three-dimensional point cloud is disclosed comprising: performing data acquisition by using a three-dimensional measurement sensor based on line structured light, and obtaining a three-dimensional point cloud data of a surface of the object after data pre-processing; eliminating influences of abnormal data and textures on extraction of sectional main profiles, to accurately obtain the sectional main profiles of the object; obtaining a binary image based on deformation feature points extracted from sections, in conjunction with a deformation feature knowledge base, and preliminarily positioning a deformation region based on sub-block images to obtain a set of target morphology sub-blocks; then performing a morphological operation on deformation feature points in the set of target morphology sub-blocks, and generating a deformation region of confidence ROC, and then performing a region growth to extract a target using ge
    Type: Grant
    Filed: January 15, 2016
    Date of Patent: August 25, 2020
    Assignee: WUHAN WUDA ZOYON SCIENCE AND TECHNOLOGY CO., LTD
    Inventors: Qingquan Li, Min Cao, Dejin Zhang, Hong Lin, Ying Chen
  • Patent number: 10743034
    Abstract: A method and apparatus are directed to applying deblocking filter to block boundaries in a video coding system including an IntraBC (Intra-block copy) mode. For at least one combination of the two neighboring reconstructed blocks including at least one IntraBC coded block in the two neighboring reconstructed blocks, a boundary filter strength equal to one or zero is selected based on coding parameters associated with the two neighboring reconstructed blocks. Deblocking filter is then applied to neighboring samples of the two neighboring reconstructed blocks around the block boundary using the boundary filter strength selected. For example, when the two neighboring reconstructed blocks correspond to one IntraBC coded block and one Inter coded block, the boundary filter strength is set to one.
    Type: Grant
    Filed: August 26, 2015
    Date of Patent: August 11, 2020
    Assignee: HFI Innovation Inc.
    Inventors: Xiaozhong Xu, Shan Liu
  • Patent number: 10725650
    Abstract: A handwritten music sign recognition device (10) has: a touch information obtaining part (21) which obtains, as position information, a position of an input means on a screen every time the input means moves, from when the input means touches the screen until when the input means is moved away therefrom; a vector information creation part (22) which creates attributes of a vector indicating a trace of movement of the input means as vector information based on the position information; and a stroke characteristic amount derivation part (23) which derives a characteristic amount of a stroke based on the vector information included in the stroke information.
    Type: Grant
    Filed: January 15, 2015
    Date of Patent: July 28, 2020
    Assignee: KABUSHIKI KAISHA KAWAI GAKKI SEISAKUSHO
    Inventor: Akihiro Fujita
  • Patent number: 10706289
    Abstract: A method, computer system, and a computer program product for analyzing a crowd using a plurality of images captured by an aerial drone is provided. The present invention may include determining a geographic area associated with the crowd. The present invention may also include partitioning the determined geographic area into a plurality of zones. The present invention may then include determining a flight path covering each zone within the plurality of zones. The present invention may further include receiving the plurality of images from the aerial drone. The present invention may also include analyzing the received plurality of images to identify a plurality of individuals associated with the crowd. The present invention may then include predicting a plurality of crowd characteristics based on the analyzed plurality of images. The present invention may further include performing an action in response to the predicted plurality of crowd characteristics.
    Type: Grant
    Filed: March 3, 2017
    Date of Patent: July 7, 2020
    Assignee: International Business Machines Corporation
    Inventors: Silpi Dhua, Anil M. Omanwar, Sujoy Sett, Pradip A. Waykos
  • Patent number: 10671835
    Abstract: The present disclosure relates to methods, devices, and systems for object recognition. For example, the systems, devices, and methods described herein may be used to recognize types, orientations and positions of objects, such as objects (e.g., planar industrial parts) in a bin picking industrial environment. In an aspect of the present disclosure, a system for object recognition may project first 3D point cloud surface data to a 2D representation data. The system may perform a matching operation to evaluate a 2D object pose of the 2D representation data and to match the 2D representation data to a 2D object template. After a match is identified, the system may project the 2D representation data to 3D space to obtain a coarse 3D object pose.
    Type: Grant
    Filed: March 5, 2018
    Date of Patent: June 2, 2020
    Assignee: Hong Kong Applied Science and Technology Research Institute Co., Ltd.
    Inventors: Cheng Zou, Shi Le Ou, Wing To Ku
  • Patent number: 10613228
    Abstract: The technology described herein is a depth camera that uses structured light and modulated light to produce a depth image. The modulated and structured light allows a time-of-flight depth to be calculated for each unit (e.g., a single dot) of the reflected structured light image captured by the depth camera's image sensor. The time-of-flight depth can be used to accurately identify each unit of the reflected structured light image. Once each unit of the reflected structured light image is identified, a structured light triangulation algorithm can be used to calculate a depth for each unit of the reflected structured light image. The present technology also allows a confidence score to be generated for the assigned depths within the depth image by comparing the structured light depth for each unit to the TOF depth for each unit.
    Type: Grant
    Filed: September 8, 2017
    Date of Patent: April 7, 2020
    Assignee: Microsoft Techology Licensing, LLC
    Inventors: Michael S. Fenton, John P. Godbaz
  • Patent number: 10593045
    Abstract: An information processing apparatus comprises a moving object detection unit configured to detect a moving object from a captured image; a passage determination unit configured to determine that the moving object has passed through a predetermined position in the captured image; an image extraction unit configured to extract a region image of the moving object that has passed through the predetermined position from the captured image; and a display control unit configured to make a display unit display, in time series, the region image for each passing direction of the moving object that has passed through the predetermined position.
    Type: Grant
    Filed: December 20, 2017
    Date of Patent: March 17, 2020
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Daisuke Nishino, Hisashi Kawabayashi
  • Patent number: 10591299
    Abstract: An information processing device includes an acquisition unit that acquires measurement success/failure information indicating whether or not measurement of a measurement unit has been successful, in a case where the measurement unit measures a distance to a subject by emitting directional light, which is light having directivity, toward the subject within a designated imaging range and receiving reflected light of the directional light, and an execution unit that causes the measurement unit to remeasure the distance to the subject in a state where a position of the designated imaging range has been changed within an allowable range in which the panoramic imaging is executable, in a case where the measurement success/failure information acquired by the acquisition unit indicates that the measurement of the measurement unit has not been successful.
    Type: Grant
    Filed: August 13, 2018
    Date of Patent: March 17, 2020
    Assignee: FUJIFILM CORPORATION
    Inventor: Tomonori Masuda
  • Patent number: 10586390
    Abstract: Disclosed is an electronic device for displaying a graphic object. The electronic device may include: a camera; a display; and a processor configured to control the display to display a first image frame acquired through the camera, to determine at least one graphic object to be displayed on the display based on a plurality of first feature points of the first image frame, to determine a location of the at least one graphic object to be displayed in a second image frame based on locations of a plurality of second feature points of the second image frame acquired through the camera and locations of the plurality of first feature points, to combine the at least one graphic object and the second image frame based on the determined locations and control the display to display the combined graphic object and second image frame.
    Type: Grant
    Filed: May 30, 2017
    Date of Patent: March 10, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Mansu Han, Joo Namkung
  • Patent number: 10551179
    Abstract: Some embodiments described herein relate to optical systems and methods for determining the shape and/or size of objects that include projecting a pattern of light onto the object. The pattern of light can be configured such that first-order reflections can be distinguished from second- and/or higher-order reflections, which can be rejected. Thus, even in instances in which the pattern of light is reflected onto the object multiple times, the original, or first-order, reflection can be detected, distinguished, and/or used for laser triangulation. In some embodiments, a pattern of light that does not have reflection and/or rotational symmetry is projected onto the object, such that second-order and/or higher-order reflections can be distinguished from the first-order reflection.
    Type: Grant
    Filed: April 29, 2019
    Date of Patent: February 4, 2020
    Assignee: Path Robotics, Inc.
    Inventors: Alexander James Lonsberry, Andrew Gordon Lonsberry
  • Patent number: 10551237
    Abstract: A method of measuring a height of a fuel in an aircraft fuel tank (21)b including illuminating the fuel in the aircraft fuel tank and detecting reflected light from the fuel. Optical coherence tomography is used to determine the height of a surface of fuel in the fuel tank. An apparatus (30) is used to measure a height of a surface of fuel in an aircraft fuel tank, and an aircraft fuel tank system with a fuel tank and an apparatus for measuring a height of a surface of fuel in the aircraft fuel tank.
    Type: Grant
    Filed: October 6, 2017
    Date of Patent: February 4, 2020
    Assignees: AIRBUS OPERATIONS LIMITED, ASTON UNIVERSITY
    Inventors: Alessio Cipullo, Neil Thomson Gordon, Kaiming Zhou
  • Patent number: 10534974
    Abstract: Provided is an image area extraction method for extracting an image area of an object from a color image of obtained color image data. The image data extraction method includes converting RGB values of each pixel in the color image data into HSV values, performing threshold processing to binarize at least one of the converted S and V values of each pixel so that it will be converted into HS?V? values, generating composite image data including an X value, a Y value, and a Z value for each pixel, the X value, the Y value, and the Z value being obtained by adding values according to predetermined one-to-one combinations between any one of an R value, a G value, and a B value and any one of an H value, an S? value, and a V? value, and extracting the image area using the composite image data.
    Type: Grant
    Filed: January 8, 2018
    Date of Patent: January 14, 2020
    Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
    Inventor: Norimasa Kobori