Classification Patents (Class 382/224)
-
Patent number: 11366967Abstract: Systems and methods are described for generating learning roadmaps from unstructured information. The systems and methods may provide for extracting a plurality of named entities from one or more corpora of information, constructing a graph based on the named entities, inducing a subgraph from the graph based on a target named entity, wherein the subgraph includes a subset of the named entities, ordering the subset of the named entities based on the subgraph, and generating a learning roadmap for the target named entity based on the ordering.Type: GrantFiled: July 24, 2019Date of Patent: June 21, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Mandar Mutalikdesai, Rahul Reddy Nimmakayala, Ashish Rao, Sheetal Srivastava, Kartikeya Vats
-
Patent number: 11367306Abstract: An autonomous mobile device (AMD) or other device may perform various tasks during operation. The AMD includes a camera to acquire an image. Some tasks, such as presenting information on a display screen or a video call, may involve the AMD determining whether a user is engaged with the AMD. The AMD may move a component, such as the camera or the display screen, to provide a best experience for an engaged user. Images from the camera are processed to determine attributes of the user, such as yaw of the face of the user, pitch of the face of the user, distance from the camera, and so forth. Based on the values of these attributes, a user engagement score is determined. The score may be used to select a particular user from many users in the image, or to otherwise facilitate operation of the AMD.Type: GrantFiled: June 23, 2020Date of Patent: June 21, 2022Assignee: AMAZON TECHNOLOGIES, INC.Inventors: Cheng-Hao Kuo, Anuja Shantaram Dawane, Che-Chun Su, Jingjing Zheng, Jim Oommen Thomas
-
Patent number: 11363150Abstract: There is provided an image management apparatus. A first receiving unit receives an image from a communication apparatus. A sending unit sends the image and an evaluation request for the image to an image evaluation apparatus configured to perform evaluation with respect to likelihood that another user will purchase the image. A second receiving unit receives an evaluation result for the image from the image evaluation apparatus. A registering unit registers the image in a server apparatus configured to provide an image sales service, in a case where the evaluation result indicates that the likelihood satisfies a predetermined standard and information, which indicates that a user consents to having the image registered in the server apparatus, is set in the image.Type: GrantFiled: February 9, 2021Date of Patent: June 14, 2022Assignee: CANON KABUSHIKI KAISHAInventors: Takahiro Matsushita, Tatsuya Nakamura
-
Patent number: 11353564Abstract: Disclosed are a disturbance light identifying apparatus, a disturbance light separating apparatus, a disturbance light identifying method, and a disturbance light separating method capable of precisely identifying whether or not light exiting an optical system contains a disturbance light component or capable of separating such a disturbance light component by using a simple technique. Provided are: a modulated light irradiation unit that irradiates an optical system 1 with modulated light; a light receiving unit that receives light exiting the optical system 1 in response to an incidence of the modulated light from the modulated light irradiation unit; and a controlling unit that controls the modulated light irradiation unit and the light receiving unit.Type: GrantFiled: December 17, 2018Date of Patent: June 7, 2022Assignee: Tamron Co., Ltd.Inventor: Kodai Yamane
-
Patent number: 11354547Abstract: System, methods, and other embodiments described herein relate to improving clustering of points within a point cloud. In one embodiment, a method includes grouping the points into cells of a grid. The grid divides an observed region of a surrounding environment associated with the point cloud into the cells. The method includes computing feature vectors for the cells that use cell features to characterize the points in the cells and relationships between the cells. The method includes analyzing the feature vectors according to a clustering model to identify clusters for the cells. The clustering model evaluates the cells to identify which of the cells belong to common entities. The method includes providing the clusters as assignments of the points to the entities depicted in the point cloud.Type: GrantFiled: March 31, 2020Date of Patent: June 7, 2022Assignee: Toyota Research Institute, Inc.Inventors: Michael James Delp, Antonio Prioletti, Matthew T. Kliemann, Randall J. St. Romain, II
-
Patent number: 11347739Abstract: A retrieval device includes a searching unit, an obtaining unit and a selecting unit. The searching unit searches a memory unit, which is stored object data that includes specific information identifying an object and attribute information indicating at least one of timing and position, for first object data containing specific information identical or similar to specified specific information. The obtaining unit obtains, from the memory unit, one or more sets of second object data which contains attribute information identical or similar to the attribute information included in the first object data and which contains specific information different than the specific information included in the first object data. The selecting unit selects one of the sets of second object data. The searching unit further searches for the first object data with the specific information included in the selected second object data serving as specified specific information.Type: GrantFiled: January 26, 2017Date of Patent: May 31, 2022Assignee: KABUSHIKI KAISHA TOSHIBAInventors: Shinichiro Hamada, Kunio Osada
-
Patent number: 11334773Abstract: Techniques for masking images based on a particular task are described. A system masks portions of an image that are not relevant to a particular task, thus, reducing the amount of data used by applications for image processing tasks. For example, images to be processed using a hair color classification model are masked so that only portions that show the person's hair are available for the model to analyze. The system configures different masker components to mask images for different tasks. A masker component can be implemented at a user device to mask images prior to sending to an application/task-specific model.Type: GrantFiled: June 26, 2020Date of Patent: May 17, 2022Assignee: Amazon Technologies, Inc.Inventors: Vivek Yadav, Aayush Gupta, Yue Wu, Pradeep Natarajan, Ayush Jaiswal
-
Patent number: 11328124Abstract: Systems and methods are described for generating learning roadmaps from unstructured information. The systems and methods may provide for extracting a plurality of named entities from one or more corpora of information, constructing a graph based on the named entities, inducing a subgraph from the graph based on a target named entity, wherein the subgraph includes a subset of the named entities, ordering the subset of the named entities based on the subgraph, and generating a learning roadmap for the target named entity based on the ordering.Type: GrantFiled: July 24, 2019Date of Patent: May 10, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Mandar Mutalikdesai, Rahul Reddy Nimmakayala, Ashish Rao, Sheetal Srivastava, Kartikeya Vats
-
Patent number: 11327194Abstract: The present disclosure discloses a method for identifying a boundary of a sedimentary facies, a computer device and a computer readable storage medium. The method comprises: acquiring a preliminary marked result of the sedimentary facies in a seismic attribute map; acquiring a color-based K-means classification result of the seismic attribute map by using a maximal between-cluster variance and a K-means clustering; acquiring a super-pixel classification result of the seismic attribute map according to a SLIC super-pixel segmentation; and performing a region growing fusion on the super-pixel classification result by taking the preliminary marked result and the K-means classification result as constraints, to determine an identification result of the boundary of the sedimentary facies in the seismic attribute map.Type: GrantFiled: August 7, 2020Date of Patent: May 10, 2022Assignee: PETROCHINA COMPANY LIMITEDInventors: Qilin Chen, Xingmiao Yao, Changkuan Ni, Bo Yan, Huaqing Liu, Guangmin Hu, Zhong Hong, Haichao Jiao
-
Patent number: 11321927Abstract: A method includes obtaining a plurality of sequential images. The method includes identifying a first plurality of pixel sets respectively associated with the plurality of sequential images. Each of the first plurality of pixel sets locates a first object within a corresponding sequential image on a per-pixel basis. The method includes determining a characterization vector of the first object by extracting a corresponding plurality of displayable characteristic values based on the first plurality of pixel sets. Each of the plurality of displayable characteristic values is associated with a corresponding pixel set and a corresponding sequential image. The characterization vector includes a plurality of distinct temporal values respectively associated with the corresponding plurality of displayable characteristic values.Type: GrantFiled: August 4, 2020Date of Patent: May 3, 2022Assignee: APPLE INC.Inventor: Ronald Vernon Ong Siy
-
Patent number: 11321955Abstract: An information processing apparatus includes a memory and a processor. The processor is connected to the memory and configured to accept input of a threshold of a confidence level indicating how confident a recognition result obtained by recognizing an image is; when the threshold whose input is accepted is applied to an actual data group constituted by one or more pieces of actual data that are recognition results accumulated as actual performance results, classify the actual data group by necessity of validation on the basis of a result of comparison between a confidence level in each of the one or more pieces of actual data in the actual data group and the threshold; and perform control to display classification results obtained by the classification.Type: GrantFiled: October 11, 2019Date of Patent: May 3, 2022Assignee: FUJIFILM Business Innovation Corp.Inventor: Takanori Ono
-
Patent number: 11321527Abstract: Techniques for machine learning using curated features are provided. A plurality of key terms is identified for a first document type of a plurality of document types. A document associated with the first document type is received, and the document is modified by inserting one or more of the plurality of key terms. A vector is generated for the modified document, and a machine learning model is trained to categorize input into the plurality of document types based on the modified document.Type: GrantFiled: January 21, 2021Date of Patent: May 3, 2022Assignee: International Business Machines CorporationInventors: Maithreyi Gopalarao, Manveer Singh Sandhu, Rohit Athradi Shetty, Amit Meel
-
Patent number: 11314803Abstract: A method for image-processing is disclosed. The method includes obtaining first image-information of an image that is to be clustered in response to a first preset condition being met; clustering the image according to the first image-information and obtaining a first clustering-result; sending an image-clustering request to a server in response to a second preset condition being met, wherein the image-clustering request is configured to indicate the server to cluster the image which has been uploaded to the server and obtain a second clustering-result; and receiving the second clustering-result returned from the first server and updating at least one of the first clustering-result and the second clustering-result according to a preset rule.Type: GrantFiled: March 13, 2020Date of Patent: April 26, 2022Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.Inventors: Xiuhua Ke, Wei Cao, Jun Wang
-
Patent number: 11315045Abstract: A weighting value is determined for each of a plurality of decision trees in a random forest model hosted on a particular device, where the weighting is based on entropy of the respective decision tree. A new decision tree is received at the particular device and a weighting value is determined for the new decision tree based on entropy of the new decision tree. Based on the determined weighting value, it is determined whether to add the new the decision tree to the random forest model. A classification for data generated at the particular device is predicted using the random forest model.Type: GrantFiled: December 29, 2016Date of Patent: April 26, 2022Assignee: Intel CorporationInventors: Yu-Lin Tsou, Shao-Wen Yang, Hong-Min Chu
-
Patent number: 11315351Abstract: The information processing device includes: a reception unit configured to receive image data regarding an accounting supporting document; a first acquisition unit configured to recognize characters in the image data and acquire the recognized characters as character data; a first identification unit configured to identify a purpose classification on the basis of the character data acquired by the first acquisition unit and the image data; an allocation unit configured to identify a standard item regarding the accounting supporting document on the basis of the character data and allocate characters to the standard item; an association unit configured to associate the characters with other characters adjacent to the characters; and an output unit configured to output the purpose classification identified by the first identification unit and the standard item and the other characters in a format in which the standard item and the other characters are associated by the association unit.Type: GrantFiled: January 8, 2020Date of Patent: April 26, 2022Assignee: Kabushiki Kaisha Genial TechnologyInventor: Akimasa Abekawa
-
Patent number: 11315033Abstract: A computer system includes a storage device and a processor configured to operate in accordance with command codes stored in the storage device. The processor places a plurality of feature vectors including feature vectors each provided with a label in a feature space. The processor determines forces among the plurality of feature vectors determined from repulsions and attractions between feature vectors. A repulsion is defined to be larger when a distance between the feature vectors is shorter, and an attraction is defined to be larger when the feature vectors have a predetermined relationship. The processor rearranges the plurality of feature vectors to reduce potential energy of the feature space determined by the forces among the plurality of feature vectors. The processor outputs at least a part of the plurality of rearranged feature vectors as data to be used for data analysis.Type: GrantFiled: March 22, 2018Date of Patent: April 26, 2022Assignee: HITACHI, LTD.Inventors: Miaomei Lei, Toshinori Miyoshi, Hiroki Sato
-
Patent number: 11308353Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor.Type: GrantFiled: October 23, 2019Date of Patent: April 19, 2022Assignee: Adobe Inc.Inventors: Mayank Singh, Puneet Mangla, Nupur Kumari, Balaji Krishnamurthy, Abhishek Sinha
-
Patent number: 11310668Abstract: The invention proposes a system and a method for transmitting a message that allows a sender (designated by an identifier) to send a digital content to one or more recipients (designated by one or more identifiers), the content being associated with at least one material subject (each designated by a single authenticator). Thus, to send a message, the sender implements at least one single authenticator of the material subject, discriminant and intrinsic characteristic of each material subject, which serves to anchor the content to transmit. To be able to access the content of the message, the recipient must provide the server not only its identifier, as for any current messaging system, but also a single authenticator with a same material subject that was used at the time the sender created the message.Type: GrantFiled: March 14, 2018Date of Patent: April 19, 2022Assignee: KERQUESTInventors: Yann Boutant, Gaël Rosset, Aurélien Hazebrouck
-
Patent number: 11300521Abstract: A method for automatic defect classification, the method may include (i) acquiring, by a first camera, at least one first image of at least one area of an object; (ii) processing the at least one first image to detect a group of suspected defects within the at least one area; (iii) performing a first classification process for initially classifying the group of suspected defects; (iii) determining whether a first subgroup of the suspected defects requires additional information from a second camera for a completion of a classification; (iv) when determining that the first subgroup of the suspected defects requires additional information from the second camera then: (a) acquiring second images, by the second camera, of the first subgroup of the suspected defects; and (b) performing a second classification process for classifying the first subgroup of suspected defects.Type: GrantFiled: June 14, 2018Date of Patent: April 12, 2022Assignee: CAMTEK LTD.Inventors: Menachem Regensburger, Daniel Buzaglo
-
Patent number: 11288823Abstract: Methods, apparatus, systems and articles of manufacture of logo recognition in images and videos are disclosed. An example method to detect a specific brand in images and video streams comprises accepting luminance images at a scale in an x direction Sx and a different scale in a y direction Sy in a neural network, and training the neural network with a set of training images for detected features associated with a specific brand.Type: GrantFiled: April 7, 2020Date of Patent: March 29, 2022Assignee: Gracenote, Inc.Inventors: Jose Pio Pereira, Kyle Brocklehurst, Sunil Suresh Kulkarni, Peter Wendt
-
Patent number: 11281893Abstract: Disclosed is to a method and to a device for modifying the affective visual information in the field of vision of a user of the device. The device includes at least one image sensor and at least one display. The method includes the following steps: Detecting an image in the field of vision of the device using an image sensor, carrying out a face recognition using the detected image for recognizing at least one face, determining the position of the eyes and mouth of the detected face, calculating a superimposition area in the display of the device in accordance with the determined positions of the eyes and mouth, superimposing the field of vision of a user of the device with alternative image data in the calculated superimposition of the display.Type: GrantFiled: June 21, 2017Date of Patent: March 22, 2022Inventor: Stefan Zechner
-
Patent number: 11282116Abstract: Image-based features may be significantly correlated with click-through rates of images that depict a product, which may provide a more formal basis for the informal notion that good quality images will result in better click-through rates, as compared to poor quality images. Accordingly, an image assessment machine is configured to analyze image-based features to improve click-through rates for shopping search applications (e.g., a product search engine). Moreover, the image assessment machine may rank search results based on image quality factors and may notify sellers about low quality images. This may have the effect of improving the brand value for an online shopping website and accordingly have a positive long-term impact on the online shopping website.Type: GrantFiled: October 29, 2019Date of Patent: March 22, 2022Assignee: eBay Inc.Inventors: Anjan Goswami, Naren Chittar, Ali Dasdan, Sanjay Pundlkrao Ghatare, Sandip Namdeo Gaikwad, Sung Hwan Chung
-
Patent number: 11282207Abstract: An image processing method performed by a computing device deployed with a deep-learning neural network is provided. An image, including an object to be segmented from the image, is acquired. The object is segmented from the image by using the deep-learning neural network to acquire a first segmentation result. Correction information input by a user with respect to the first segmentation result is acquired. Based on correction information, the first segmentation result is modified by using the deep-learning neural network, to acquire a second segmentation result.Type: GrantFiled: June 16, 2020Date of Patent: March 22, 2022Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LTDInventors: Yurong Dai, Qi Fan
-
Patent number: 11281962Abstract: In certain embodiments, content items may be obtained, where each of the content items may include multiple data types. Machine learning models may be caused to be trained based on the content items to map data in a vector space by providing at least a first portion of each of the content items as input to at least one of the machine learning models and providing at least a second portion of each of the content items as input to at least another one of the machine learning models. A search request for results may be obtained, where the search request includes search parameters. One or more locations within the vector space may be predicted (e.g., by one or more of the machine learning models) based on the search parameters. Information (indicating content items mapped to or proximate the predicted locations) may be provided as a request response.Type: GrantFiled: September 27, 2017Date of Patent: March 22, 2022Assignee: Clarifai, Inc.Inventors: Matthew Zeiler, David Eigen, Ryan Compton, Christopher Fox
-
Patent number: 11275942Abstract: A method for generating training data can include: determining a set of images; determining a set of masks based on the images; determining a first mesh based on the set of masks; optionally determining a refined mesh by recomputing the first mesh; optionally determining one or more faces of the refined mesh; optionally adding one or more keypoints to the refined mesh; optionally determining a material property set for the object; optionally generating a full object mesh; determining one or more scenes; optionally determining training data based on the one or more scenes; optionally training one or more object detectors using the training data; and detecting one or more objects using the trained object detector.Type: GrantFiled: July 14, 2021Date of Patent: March 15, 2022Assignee: Vicarious FPC, Inc.Inventors: Eyrun Eyjolfsdottir, Michael Stark, Marco Carra, Manushree Gangwar, Alex Schlegel, Karthikeyan Yuvaraj, Dennis Park, David A. Mely, Anna Chen, Sivaramakrishnan Swaminathan
-
Patent number: 11276034Abstract: One variation of a method for tracking stock level within a store includes: dispatching a robotic system to image shelving structures within the store during a scan cycle; receiving images from the robotic system, each image recorded by the robotic system during the scan cycle and corresponding to one waypoint within the store; identifying, in the images, empty slots within the shelving structures; identifying a product assigned to each empty slot based on product location assignments defined in a planogram of the store; for a first product of a first product value and assigned to a first empty slot, generating a first prompt to restock the first empty slot with a unit of the first product during the scan cycle; and, upon completion of the scan cycle, generating a global restocking list specifying restocking of a set of empty slots associated with product values less than the first product value.Type: GrantFiled: February 14, 2020Date of Patent: March 15, 2022Assignee: Simbe Robotics, Inc.Inventors: Mirza Akbar Shah, Bradley Bogolea, Jeffrey Gee
-
Patent number: 11270157Abstract: The present disclosure provides a system and method for classification determination of a structure. The method may include obtaining image data representing a structure of a subject. The method may also include determining a plurality of candidate classifications of the structure and their respective probabilities by inputting the image data into a classification model. The classification model may include a backbone network for determining a backbone feature of the structure, a segmentation network for determining a segmentation feature of the structure, and a density classification network for determining a density feature of the structure. The method may further include determining a target classification of the structure based on at least a part of the probabilities of the plurality of candidate classifications.Type: GrantFiled: December 27, 2019Date of Patent: March 8, 2022Assignee: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.Inventors: Yanbo Chen, Yaozong Gao, Yiqiang Zhan
-
Patent number: 11244193Abstract: Provided herein is a method, apparatus, and computer program product for classifying objects as static objects or dynamic objects based on point cloud data. Methods may include: receiving point cloud data representative of an environment; computing voxel sequences from the point cloud data; extracting voxel-wise semantic features from the voxel sequences; modeling voxel-wise temporal changes based on the voxel-wise semantic features; and classifying objects in the environment as dynamic objects or static objects based on the modeled voxel-wise temporal changes. Computing voxel sequences from the point cloud data may include using a voxel cloud connectivity segmentation method to group voxels in point clouds into perceptually meaningful regions.Type: GrantFiled: August 7, 2019Date of Patent: February 8, 2022Assignee: HERE GLOBAL B.V.Inventor: Shubhabrata Roy
-
Patent number: 11238316Abstract: Implementations described herein relate to methods, systems, and computer-readable media to detect counterfeit virtual three-dimensional (3D) objects. In some implementations, a computer-implemented method includes receiving an unauthenticated virtual 3D object. The method further includes determining a plurality of two-dimensional (2D) views of the unauthenticated virtual 3D object. In some implementations, the plurality of 2D views include at least two 2D views and each view of the plurality of 2D views is captured from a respective viewpoint. The method further includes calculating a hash value for each 2D view of the plurality of 2D views. The method further includes determining whether the respective hash values of at least two of the plurality of 2D views match hash values of corresponding 2D views of an authentic virtual 3D object and if it is determined that the respective hash values match, classifying the unauthenticated virtual 3D object as a counterfeit object.Type: GrantFiled: December 4, 2019Date of Patent: February 1, 2022Assignee: Roblox CorporationInventors: Robin E. Mayes, Courtland R. Caldwell, Rebecca L. Herndon, Hariharan Natarajan
-
Patent number: 11238722Abstract: The methods and systems are designed to utilize an integrated combination of just in time, just in place, and just on device actions connected to an image recognition process for monitoring criminals who are probation, offenders who are on parole, sex offenders, and witnesses under protection by law enforcement.Type: GrantFiled: October 15, 2019Date of Patent: February 1, 2022Assignee: OPTIMUM ID LLCInventors: Hemanshu Nigam, Michael Lang, James Drolshagen
-
Patent number: 11232306Abstract: A display apparatus includes a communication interface, a camera, a display and a processor configured to receive information on a plurality of images including a first object image corresponding to an identical type of an object selected by a user and a second object image included in each of the plurality of images. The processor is configured to identify one from a plurality of images based on information on a third object image identified from an image photographed through the camera and the received second object image, and control the display to display an obtained image based on the identified image, a fourth object image corresponding to an object selected by the user, and the third object image is displayed.Type: GrantFiled: November 18, 2019Date of Patent: January 25, 2022Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyeseon Heo, Kyoungjae Park, Youngchun Ahn
-
Patent number: 11232647Abstract: Methods and devices for generating reference data for adjusting a digital representation of a head region, and methods and devices for adjusting the digital representation of a head region are disclosed. In some arrangements, training data are received. A first machine learning algorithm generates first reference data using the training data. A second machine learning algorithm generates second reference data using the same training data and the first reference data generated by the first machine learning algorithm.Type: GrantFiled: July 23, 2020Date of Patent: January 25, 2022Assignee: RealD Spark, LLCInventors: Eric Sommerlade, Alexandros Neophytou
-
Patent number: 11233952Abstract: Systems, devices, media and methods are presented for presentation of modified objects within a video stream. The systems and methods select an object of interest depicted within a user interface based on an associated image modifier, determine a modifier context based at least in part on one or more characteristics of the selected object, identify a set of image modifiers based on the modifier context, rank a first portion of the identified set of image modifiers based on a primary ordering characteristic, rank a second portion of the identified set of image modifiers based on a secondary ordering characteristic and cause presentation of the modifier icons for the ranked set of image modifiers.Type: GrantFiled: March 11, 2020Date of Patent: January 25, 2022Assignee: Snap Inc.Inventors: Ebony James Charlton, Michael John Evans, Samuel Edward Hare, Andrew James McPhee, Robert Cornelius Murphy, Eitan Pilipski
-
Patent number: 11216496Abstract: Roughly described, a system for user identification of a desired document. A database is provided which identifies a catalog of documents in an embedding space, the database identifying a distance in the embedding space between each pair of documents corresponding to a predetermined measure of dissimilarity between the pair of documents. The system presents an initial collection of the documents toward the user, from an initial candidate space which is part of the embedding space. The system then iteratively refines the candidate space using geometric constraints on the embedding space determined in response to relative feedback by the user. At each iteration the system identifies to the user a subset of documents from the then-current candidate space, based on which the user provides the relative feedback. In an embodiment, these subsets of documents are more discriminative than the average discriminativeness of similar sets of documents in the then-current candidate space.Type: GrantFiled: November 12, 2019Date of Patent: January 4, 2022Assignee: Evolv Technology Solutions, Inc.Inventor: Nigel Duffy
-
Patent number: 11216659Abstract: A system and method of processing source data that includes table data by converting the table data into machine encoded text data having associated therewith text coordinate data having a Y-axis component and an X-axis component, and then generating from the machine encoded text data a plurality of pixels along the Y-axis component and the X-axis component. The system then performs a clustering technique on the plurality of pixels to generate a plurality of clusters of pixels based on similar attributes, and classifying each of the plurality of clusters of pixels as a selected row of the table and as a selected column of the table, thus making available the information encoded in the table for subsequent processing.Type: GrantFiled: January 13, 2020Date of Patent: January 4, 2022Assignee: KPMG LLPInventors: Raghuram Srinivas, Marisa Ferrara Boston, Vishnu Muralidharan, Seth Harsh
-
Patent number: 11210524Abstract: A method and an apparatus for outputting information are provided according to embodiments of the disclosure. The method includes: recognizing a target video, to recognize at least one entity and obtain a confidence degree of each entity, the entity including a main entity and related entities; matching the at least one entity with a pre-stored knowledge base to determine at least one candidate entity; obtaining at least one main entity by expanding the related entities of the at least one candidate entity based on the knowledge base, and obtaining a confidence degree of the obtained main entity; and calculating a confidence level of the obtained main entity based on the confidence degree of each of the related entities of the at least one candidate entity and the confidence degree of the obtained main entity, and outputting the confidence level of the obtained main entity.Type: GrantFiled: March 2, 2020Date of Patent: December 28, 2021Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.Inventors: Kexin Ren, Xiaohan Zhang, Zhifan Feng, Yang Zhang
-
Patent number: 11207995Abstract: A method includes causing, with a controller, operation of a first compaction machine at a worksite based at least in part on a worksite plan. The method also includes determining, with the controller, a return path extending from a current location of the first machine to a charging zone located at the worksite, and determining, with the controller, a return power required for the first machine to traverse the return path. The method further includes causing, with the controller, the first machine to traverse the return path, from the current location to the charging zone, based on at least one of the return power and an amount of available power stored in an energy storage device of the first machine.Type: GrantFiled: July 8, 2019Date of Patent: December 28, 2021Assignee: Caterpillar Paving Products Inc.Inventor: John L. Marsolek
-
Patent number: 11205065Abstract: Disclosed herein are systems, devices, and processes for gesture detection. A method includes capturing a series of images. The method includes generating motion isolation information based on the series of images. The method includes generating a composite image based on the motion isolation information. The method includes determining a gesture based on the composite image. The processes described herein may include the use of convolutional neural networks on a series of time-related images to perform gesture detection on embedded systems or devices.Type: GrantFiled: October 18, 2019Date of Patent: December 21, 2021Assignee: ALPINE ELECTRONICS OF SILICON VALLEY, INC.Inventors: Diego Rodriguez Risco, Samir El Aouar, Alexander Joseph Ryan
-
Patent number: 11200667Abstract: Disclosed prostate computer aided diagnosis (CAD) systems employ a Random Forest classifier to detect prostate cancer. System classify individual pixels inside the prostate as potential sites of cancer using a combination of spatial, intensity and texture features extracted from three sequences. The Random Forest training considers instance-level weighting for equal treatment of small and large cancerous lesions and small and large prostate backgrounds. Two other approaches are based on an AutoContext pipeline intended to make better use of sequence-specific patterns. Also disclosed are methods and systems for accurate automatic segmentation of the prostate in MRI. Methods can include both patch-based and holistic (image-to-image) deep learning methods for segmentation of the prostate. A patch-based convolutional network aims to refine the prostate contour given an initialization. A method for end- to-end prostate segmentation integrates holistically nested edge detection with fully convolutional networks.Type: GrantFiled: February 22, 2018Date of Patent: December 14, 2021Assignee: The United States of America, as represented by the Secretary, Department of Health and Human ServicesInventors: Nathan S. Lay, Yohannes Tsehay, Ronald M. Summers, Baris Turkbey, Matthew Greer, Ruida Cheng, Holger Roth, Matthew J. McAuliffe, Sonia Gaur, Francesca Mertan, Peter Choyke
-
Patent number: 11200464Abstract: An information processing method includes: inputting sample image into a machine learning architecture to obtain a first feature, and causing a first classifier to calculate a first classification loss; calculating a second feature based on the first feature and a predetermined first mask, and inputting the second feature into the first classifier to calculate an entropy loss; calculating a second mask based on the first mask and the entropy loss to maximize the entropy loss; obtaining an adversarial feature based on the first feature and the second mask, where the adversarial feature is complementary to the second feature; causing, by training the first classifier and the second classifier in association with each other, the second classifier to calculate a second classification loss based on the adversarial feature; and adjusting parameters of the machine learning architecture, the first classifier and the second classifier, to obtain a trained machine learning architecture.Type: GrantFiled: January 16, 2020Date of Patent: December 14, 2021Assignee: FUJITSU LIMITEDInventors: Wei Shen, Rujie Liu
-
Patent number: 11176381Abstract: Various embodiments describe video object segmentation using a neural network and the training of the neural network. The neural network both detects a target object in the current frame based on a reference frame and a reference mask that define the target object and propagates the segmentation mask of the target object for a previous frame to the current frame to generate a segmentation mask for the current frame. In some embodiments, the neural network is pre-trained using synthetically generated static training images and is then fine-tuned using training videos.Type: GrantFiled: April 23, 2020Date of Patent: November 16, 2021Assignee: Adobe Inc.Inventors: Joon-Young Lee, Seoungwug Oh, Kalyan Krishna Sunkavalli
-
Patent number: 11170215Abstract: Captured samples of a physical structure or other scene are mapped to a predetermined multi-dimensional coordinate space, and spatially-adjacent samples are organized into array cells representing subspaces thereof. Each cell is classified according to predetermined target-identifying criteria for the samples of the cell. A cluster of spatially-contiguous cells of common classification, peripherally bounded by cells of different classification, is constructed, and a boundary demarcation is defined from the peripheral contour of the cluster. The boundary demarcation is overlaid upon a visual display of the physical scene, thereby visually demarcating the boundaries of a detected target of interest.Type: GrantFiled: April 28, 2017Date of Patent: November 9, 2021Assignee: REALITY ANALYTICS, INC.Inventor: Jeffrey Mark Sieracki
-
Patent number: 11164283Abstract: A feature extractor determines reference feature locations from a portion of a reference image and corresponding feature locations from a portion of a warp image. A transform module determines a homography transform function that transforms versions of the corresponding feature locations to the reference feature locations. The homography transform function has an error below a threshold level, where the error represents a difference between the transformed corresponding feature locations and the reference feature locations. The local transform module generates transform parameters by processing the homography transform function. A warper circuit warps the portion of the warp image by at least applying the transform parameters to generate a portion of a warped image.Type: GrantFiled: April 24, 2020Date of Patent: November 2, 2021Assignee: Apple Inc.Inventors: Kaiming Liu, Maxim Smirnov, David R. Pope
-
Patent number: 11164042Abstract: A computing system includes an encoder that receives an input image and encodes the input image into real image features, a decoder that decodes the real image features into a reconstructed image, a generator that receives first audio data corresponding to the input image and generates first synthetic image features from the first audio data, and receives second audio data and generates second synthetic image features from the second audio data, a discriminator that receives both the real and synthetic image features and determines whether a target feature is real or synthetic, and a classifier that classifies a scene of the second audio data based on the second synthetic image features.Type: GrantFiled: April 9, 2020Date of Patent: November 2, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Eric Chris Wolfgang Sommerlade, Yang Liu, Alexandros Neofytou, Sunando Sengupta
-
Patent number: 11163877Abstract: The present disclosure discloses an information processing method, including the steps of acquiring at least one executable file of a specified type; extracting a first operation instruction from the at least one executable file of the specified type; determining the first operation instruction as a feature instruction if a preset policy is met; extracting a feature value of the feature instruction; constructing a virus classification model based on the feature value of the feature instruction for obtaining a virus structural feature parameter; extracting a second operation instruction from at least one to-be-analyzed file when the at least one to-be-analyzed file is identified according to the virus classification model; and identifying the to-be-analyzed file as a virus file if the feature value of the second operation instruction corresponds to the virus structural feature parameter.Type: GrantFiled: September 11, 2017Date of Patent: November 2, 2021Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Shujie Lin, Yi Yang, Luxin Li, Tao Yu
-
Patent number: 11164047Abstract: The present disclosure provides a computer-implemented method, computer system and computer program product for object detection. According to the computer-implemented method, a first object can be classified to be a first category based on detection data acquired in a detection area. Then, a confidence score for the first category can be calculated based on historical detection data of the detection area, wherein the confidence score presents possibility degree of at least one object of the first category existing in the detection area. Whether classification of the first object is abnormal can be determined based on the confidence score.Type: GrantFiled: July 22, 2019Date of Patent: November 2, 2021Assignee: International Business Machines CorporationInventors: Ke Wei Sun, Junsong Wang, Yan GY Gong, Rong Yan, Yonghua Lin, Jie Zhang
-
Patent number: 11158351Abstract: Aspects of the present disclosure involve a system comprising a storage medium storing a program and method for receiving a video comprising a plurality of video segments; selecting a target action sequence that includes a sequence of action phases; receiving features of each of the video segments; computing, based on the received features, for each of the plurality of video segments, a plurality of action phase confidence scores indicating a likelihood that a given video segment includes a given action phase of the sequence of action phases; identifying a set of consecutive video segments of the plurality of video segments that corresponds to the target action sequence, wherein video segments in the set of consecutive video segments are arranged according to the sequence of action phases; and generating a display of the video that includes the set of consecutive video segments and skips other video segments in the video.Type: GrantFiled: December 20, 2018Date of Patent: October 26, 2021Assignee: Snap Inc.Inventors: Zhou Ren, Yuncheng Li, Ning Xu, Enxu Yan, Tan Yu
-
Patent number: 11138462Abstract: A method includes receiving, with a computing system, a video item. The method further includes identifying a first set of features within a first frame of the video item. The method further includes identifying, with the computing system, a second set of features within a second frame of the video item, the second frame being subsequent to the first frame. The method further includes determining, with the computing system, differences between the first set of features and the second set of features. The method further includes assigning a clip category to a clip extending between the first frame and the second frame based on the differences.Type: GrantFiled: January 7, 2020Date of Patent: October 5, 2021Assignee: Netflix, Inc.Inventor: Apurvakumar Dilipkumar Kansara
-
Patent number: 11138437Abstract: Provided are an image processing apparatus and method. The image processing apparatus includes a decoder configured to decode image frames of an image; an image quality controller configured to obtain a genre recognition confidence of a previous image frame and a genre recognition confidence of a current image frame, and identify image quality control factor value, based on the genre recognition confidence of the previous image frame and the genre recognition confidence of the current image frame; and an image quality processor configured to image-quality process at least one of the decoded image frames by using the image quality control factor value, and output the processed at least one of the decoded image frames.Type: GrantFiled: November 15, 2019Date of Patent: October 5, 2021Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Daesung Cho, Wooseok Kang, Ilhyun Cho
-
Patent number: 11127165Abstract: An aerial imaging system is disclosed. The aerial imaging system includes an aerial vehicle; a camera system mounted on the aerial vehicle; and an image storage medium. The camera system includes a lens and a plurality of image sensors. The plurality of image sensors includes a reference image sensor and a plurality of fixed wavelength sensors. The reference image sensor is configured to capture images including light at a plurality of wavelength ranges and to output a multilayer image. The plurality of fixed wavelength sensors are each configured to capture images including light at a selected wavelength range and to each output a single layer image. The image storage medium is configured to store the multilayer image and the plurality of single layer images.Type: GrantFiled: December 2, 2019Date of Patent: September 21, 2021Assignee: Sentera, Inc.Inventor: Dimitris Zermas