Patents Examined by Sean M Conner
-
Patent number: 11663642Abstract: Systems and methods are provided for receiving at least a first query color, and searching an electronic catalog including a plurality of product images for the first query color to determine a similarity measure between the first query color and a product image of a plurality of product images. The similarity measure may be determined by determining a Euclidean distance between values in a three-dimensional color space for the first query color and a target color of the product image, and determining the similarity measure between the query color and the product image by determining a sum of the similarity measures from all target colors on the product image, weighted by the coverage of each target color. The search results may be transmitted based on the searching of the electronic catalog including the plurality of product images for the first query color.Type: GrantFiled: October 7, 2019Date of Patent: May 30, 2023Assignee: Salesforce, Inc.Inventors: Michael Sollami, Yang Zhang
-
Patent number: 11663823Abstract: Dual-modality relation networks for audio-visual event localization can be provided. A video feed for audio-visual event localization can be received. Based on a combination of extracted audio features and video features of the video feed, informative features and regions in the video feed can be determined by running a first neural network. Based on the informative features and regions in the video feed determined by the first neural network, relation-aware video features can be determined by running a second neural network. Based on the informative features and regions in the video feed, relation-aware audio features can be determined by running a third neural network. A dual-modality representation can be obtained based on the relation-aware video features and the relation-aware audio features by running a fourth neural network. The dual-modality representation can be input to a classifier to identity an audio-visual event in the video feed.Type: GrantFiled: August 10, 2020Date of Patent: May 30, 2023Assignee: International Business Machines CorporationInventors: Chuang Gan, Dakuo Wang, Yang Zhang, Bo Wu, Xiaoxiao Guo
-
Patent number: 11651288Abstract: A learning data generation device of an embodiment includes a detection unit that detects a changed region in a space between a first map and a second map based on first map data which indicate the first map and second map data which indicate the second map which indicates a substantially same space as the first map and represents the space at a different time point from the first map and a changed region image acquisition unit that acquires images which correspond to the changed region detected by the detection unit from a first image in which the space represented by the first map is captured and a second image in which the space represented by the second map is captured.Type: GrantFiled: April 5, 2019Date of Patent: May 16, 2023Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Motohiro Takagi, Kazuya Hayase, Tokinobu Mitasaki, Atsushi Shimizu
-
Patent number: 11651049Abstract: A computer-implemented method to capture and detect clusters in, or determined by, a set V of discrete digital data comprising; computing, from the set V, an abstract separation system ASS that consists of a finite set S, whose elements are called separations; of a predetermined transitive, antisymmetric and reflexive order relation ? on S; and of an order-reversing involution *: S?S, that is, a mapping s?s* with the property that, (s*)*=s and that r?s implies s*<r* for all r, s?S; predetermining a set of consistency requirements (CRs), that is, a set F of subsets of S; computing, from the ASS (S,?, *), one or more abstract tangles, that is, any set T?S that contains exactly one of each pair {s, s*} for s?S, and does not contain any of the forbidden configurations F?F as a subset; or determining that there is no abstract tangle; and determining that any abstract tangle T represents a cluster in, or determined by, the data set V.Type: GrantFiled: April 13, 2017Date of Patent: May 16, 2023Assignees: Universitat Hamburg, Victoria Link LimitedInventors: Reinhard Diestel, Geoffrey Whittle
-
Patent number: 11636177Abstract: Disclosed are an object detection dataset construction method using image entropy and a data processing device performing the same. The data processing device includes an input unit configured to receive multiple images, a control unit configured to choose processing priorities of the received multiple images using image entropy and construct an object detection dataset from a corresponding image according to the chosen processing priorities, and a storage unit configured to store the constructed object detection dataset.Type: GrantFiled: November 23, 2020Date of Patent: April 25, 2023Assignee: Konan Technology Inc.Inventors: Hyunsu Kang, Euncheol Kang
-
Patent number: 11631003Abstract: Techniques for predicting states may include: receiving data sets of counter values, wherein each counter values denotes a number of times a particular code flow point associated with the counter value is executed at runtime during a specified time period; receiving images generated from the data sets; labeling each of the images with state information, wherein first state information associated with a first image indicates that the first image is associated with a first error state of a system or an application; training a neural network using the images to recognize the first state; receiving a next image generated from another data set; and predicting, by the neural network and in accordance with the next image, whether the system or the application is expected to transition into the first state. In at least one embodiment, the foregoing processing may optionally use matrices generated from the data sets rather than images.Type: GrantFiled: June 30, 2020Date of Patent: April 18, 2023Assignee: EMC IP Holding Company LLCInventors: Owen Martin, Benjamin A. Randolph, Scott J. Romano, Hani Zaitoun, Abhilash Sanap
-
Patent number: 11631176Abstract: A method includes obtaining image(s) of a dental device, determining file(s) including at least one of a first model of the dental device or a second model of a mold, determining an intended property for the dental device based on at least one of the first model or the second model, and determining an actual property of the dental device from the image(s). The method further includes determining whether a cutline variation, an arch variation, and/or a bend of the dental device is detected between the dental device and the first model and/or the second model by comparing the intended property with the actual property. The method further includes determining whether there is a possible defect in the dental device based on whether the cutline variation exceeds a cutline variation threshold, the arch variation exceeds an arch variation threshold, and/or the bend exceeds a bend threshold.Type: GrantFiled: March 18, 2022Date of Patent: April 18, 2023Assignee: Align Technology, Inc.Inventors: Anatoliy Parpara, Ivan Kharpalev, Stephan Albert Alexandre Dumothier, Andrey Cherkas, Alexey Kalinichenko, Jack Shaw, Israel Velazquez
-
Patent number: 11631234Abstract: The present disclosure relates to an object selection system that accurately detects and optionally automatically selects user-requested objects (e.g., query objects) in digital images. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of a query object. In particular, the object selection system can identify both known object classes as well as objects corresponding to unknown object classes.Type: GrantFiled: July 22, 2019Date of Patent: April 18, 2023Assignee: Adobe, Inc.Inventors: Scott Cohen, Zhe Lin, Mingyang Ling
-
Patent number: 11631175Abstract: A multi-label heat map generating system is operable to receive a plurality of medical scans and a corresponding plurality of medical labels that each correspond to one of a set of abnormality classes. A computer vision model is generated by training on the medical scans and the medical labels. Probability matrix data, which includes a set of image patch probability values that each indicate a probability that a corresponding one of the set of abnormality classes is present in each of a set of image patches, is generated by performing an inference function that utilizes the computer vision model on a new medical scan. Preliminary heat map visualization data can be generated for transmission to a client device based on the probability matrix data. Heat map visualization data can be generated via a post-processing of the preliminary heat map visualization data to mitigate heat map artifacts.Type: GrantFiled: February 8, 2022Date of Patent: April 18, 2023Assignee: Enlitic, Inc.Inventors: Kevin Lyman, Eric C. Poblenz, Li Yao, Ben Covington, Anthony Upton
-
Patent number: 11615264Abstract: Presented herein are systems and methods of clustering images using encoder-decoder models. A computing system may identify tiles derived from an image. Each tile may have a first dimension. The computing system may apply an image reconstruction model to the tiles. The image reconstruction model may include an encoder block having a first set of weights to generate embedding representations corresponding to the tiles. Each embedding representation may have a second dimension lower than the first dimension. The image reconstruction model may include a decoder block having a second set of weights to generate reconstructed tiles corresponding to the embedding representations. The computing system may apply a clustering model comprising a feature space to the embedding representations to classify each tile to one of a plurality of conditions.Type: GrantFiled: March 5, 2020Date of Patent: March 28, 2023Assignee: Memorial Sloan Kettering Cancer CenterInventors: Thomas J. Fuchs, Hassan Muhammad
-
Patent number: 11587323Abstract: A machine accesses a set of image target models, each image target model being associated with model parameters, the model parameters comprising at least an operational domain, an expected input image quality, and an expected orientation. The machine receives an image for processing by one or more image target models from the set, the image including metadata specifying image parameters of the received image. The machine identifies, based on the image parameters in the metadata of the received image and the model parameters of one or more models in the set, a first subset of the set of image target models including image target models that are capable of processing the received image. The machine provides the received image to at least one image target model in the first subset.Type: GrantFiled: May 14, 2020Date of Patent: February 21, 2023Assignee: Raytheon CompanyInventor: Steven A. Israel
-
Patent number: 11586848Abstract: An object recognition device including an artificial neural network (NN) engine configured to receive learning data and weights, make an object recognition model (ORM) learn by using the received information, and provide selected weight data including weights from the selected portion of the weights, and further configured to receive a feature vector, and apply the feature vector extracted from an object data that constructs the object and the selected weight data to the learned ORM to provide an object recognition result, a nonvolatile memory (NVM) configured to store the learned ORM, and an error correction code (ECC) engine configured to perform an ECC encoding on the selected weight data to generate parity data, provide the selected weight data and the parity data to the NVM, and provide the selected weight data to the NN engine by performing an ECC decoding on the selected weight data based on the parity data.Type: GrantFiled: February 6, 2019Date of Patent: February 21, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Eun-Jin Yun, Sung-Joon Kim, Sang-Hoan Chang
-
Patent number: 11580635Abstract: The invention provides a fluid analysis apparatus, a method for operating a fluid analysis apparatus, and a fluid analysis program that perform display such that the tendency of a fluid flow in a blood vessel is easily checked. Route position information that is capable of identifying an order along a route of the anatomical structure is assigned to each position in the anatomical structure, using three-dimensional volume data in which each voxel has the information of a three-dimensional flow velocity vector indicating a flow velocity of a fluid in an anatomical structure. The three-dimensional flow velocity vector is selected such that the route position information of a position where the three-dimensional flow velocity vector is present is sequentially arranged from one point in the anatomical structure and a trajectory indicating the flow of the fluid is drawn so as to be visibly recognized.Type: GrantFiled: February 4, 2020Date of Patent: February 14, 2023Assignee: FUJIFILM CorporationInventor: Hirotaka Ito
-
Patent number: 11557133Abstract: Automatic license plate recognition occurs when a light sensor that continually captures video detects motion as a vehicle is driven through a gate. The light sensor detects the vehicle and license plate in the video stream captured by the light sensor. An algorithm associated with the video stream of the light sensor is trained to detect license plates. The light sensor starts executing the recognition algorithm when it detects motion. Recognition of characters in the license plate is based upon an aggregation of several captured video frames in which a license plate is detected.Type: GrantFiled: July 22, 2022Date of Patent: January 17, 2023Assignee: Verkada Inc.Inventors: Yi Xu, Yunchao Gong, Suraj Arun Vathsa, Mayank Gupta, Naresh Nagabushan
-
Patent number: 11551376Abstract: There is provided a method and system for determining if a head-mounted device for extended reality (XR) is correctly positioned on a user, and optionally performing a position correction procedure if the head-mounted device is determined to be incorrectly positioned on the user. Embodiments include: performing eye tracking by estimating, based on a first image of a first eye of the user, a position of a pupil in two dimensions; determining whether the estimated position of the pupil of the first eye is within a predetermined allowable area in the first image; and, if the determined position of the pupil of the first eye is inside the predetermined allowable area, concluding that the head-mounted device is correctly positioned on the user; or, if the determined position of the pupil of the first eye is outside the predetermined allowable area, concluding that the head-mounted device is incorrectly positioned on the user.Type: GrantFiled: October 25, 2019Date of Patent: January 10, 2023Assignee: TOBII ABInventors: Joakim Zachrisson, Mikael Rosell, Carlos Pedreira, Mark Ryan, Simon Johansson
-
Patent number: 11551795Abstract: A multi-label heat map generating system is operable to receive a plurality of medical scans and a corresponding plurality of global labels that each correspond to one of a set of abnormality classes. A computer vision model is generated by training on the medical scans and the global labels. Probability matrix data, which includes a set of image patch probability values that each indicate a probability that a corresponding one of the set of abnormality classes is present in each of a set of image patches, is generated by performing an inference function that utilizes the computer vision model on a new medical scan. Heat map visualization data can be generated for transmission to a client device based on the probability matrix data that indicates, for each of the set of abnormality classes, a color value for each pixel of the new medical scan.Type: GrantFiled: February 8, 2022Date of Patent: January 10, 2023Assignee: Enlitic, Inc.Inventors: Li Yao, Jordan Prosky, Eric C. Poblenz, Kevin Lyman, Lionel Lints, Ben Covington, Anthony Upton
-
Patent number: 11544507Abstract: An apparatus and method to train an image recognition model to accurately estimate a location of a reference point for each class of landmark is disclosed. The apparatus and method use the image recognition model, which is trained based on calculating a class loss and a class-dependent localization loss from training data based on an image recognition model and training the image recognition model using a total loss comprising the class loss and the localization loss.Type: GrantFiled: March 28, 2019Date of Patent: January 3, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Wonhee Lee, Minjung Son, Kyungboo Jung, Hyun Sung Chang
-
Patent number: 11537884Abstract: This application relates to a machine learning model training method and apparatus, and an expression image classification method and apparatus. The machine learning model training method includes: obtaining a machine learning model that includes a model parameter and that is obtained through training according to a general-purpose image training set; determining a sample of a special-purpose image and a corresponding classification label; inputting the sample of the special-purpose image to the machine learning model, to obtain an intermediate classification result; and adjusting the model parameter of the machine learning model according to a difference between the intermediate classification result and the classification label, continuing training, and ending the training in a case that a training stop condition is met. The solutions provided in this application improve the training efficiency of the machine learning model.Type: GrantFiled: January 6, 2020Date of Patent: December 27, 2022Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Longpo Liu, Wei Wan, Qian Chen
-
Patent number: 11531829Abstract: An automatic image annotation system receives a reference image with one or more parts annotated along with one or more query images and automatically identifies portions from the query images that are similar to the annotated parts of the reference image. The S-matrices of the reference image and the query images are obtained via singular value decomposition (SVD). Lower-dimensional images are also obtained for the reference image and the query images using a pre-trained deep learning model. The S-matrices and the lower-dimensional images of the corresponding images are combined to generate vector representations. A distance metric is calculated for the vector representation of the reference image with that of the query image. A preliminary output image with a preliminary annotation is initially generated. The preliminary annotation is further optimized to generate an optimized annotation that adequately covers the region of interest (ROI).Type: GrantFiled: July 24, 2020Date of Patent: December 20, 2022Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Sridhar Murugaraj, Indrajit Kar, Vishal Pandey, Sushresulagna Rath
-
Patent number: 11527084Abstract: A system and method for generating a bounding box for an object in proximity to a vehicle are disclosed. The method includes: receiving a three-dimensional (3D) point cloud representative of an environment; receiving a two-dimensional (2D) image of the environment; processing the 3D point cloud to identify an object cluster of 3D data points for a 3D object in the 3D point cloud; processing the 2D image to detect a 2D object in the 2D image and generate information regarding the 2D object from the 2D image; and when the 3D object and the 2D object correspond to the same object in the environment: generating a bird's eye view (BEV) bounding box for the object based on the object cluster of 3D data points and the information from the 2D image.Type: GrantFiled: July 10, 2020Date of Patent: December 13, 2022Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Ehsan Taghavi, Amirhosein Nabatchian, Bingbing Liu