Patents Examined by Tsung-Yin Tsai
  • Patent number: 11398098
    Abstract: Advanced driver assistance systems can be designed to recognize and to classify traffic signs under real time constraints, and under a wide variety of visual conditions. This disclosure provides techniques that employ binary masks extracted by color space segmentation, with a different binary mask generated for each sign shape. Temporal tracking is employed to add robustness to the detection system. The system is generic, and is trainable to the traffic signs used in various countries.
    Type: Grant
    Filed: May 1, 2020
    Date of Patent: July 26, 2022
    Assignee: Texas Instruments Incorporated
    Inventors: Arun Shankar Kudana, Manu Mathew, Soyeb Nagori
  • Patent number: 11392211
    Abstract: The technology disclosed relates to operating a motion-capture system responsive to available computational resources. In particular, it relates to assessing a level of image acquisition and image-analysis resources available using benchmarking of system components. In response, one or more image acquisition parameters and/or image-analysis parameters are adjusted. Acquisition and/or analysis of image data are then made compliant with the adjusted image acquisition parameters and/or image-analysis parameters. In some implementations, image acquisition parameters include frame resolution and frame capture rate and image-analysis parameters include analysis algorithm and analysis density.
    Type: Grant
    Filed: July 23, 2020
    Date of Patent: July 19, 2022
    Assignee: Ultrahaptics IP Two Limited
    Inventor: David Holz
  • Patent number: 11393223
    Abstract: A periphery monitoring device includes: an acquisition unit that acquires capture images which are captured by an imaging unit in time series when a vehicle is moving, the imaging unit being provided in the vehicle and capable of imaging surroundings of the vehicle; and a restoration processing unit that, in a case where dirt is present in a latest capture image among the capture images, inputs the capture images into a first learned model and generates a first restoration image as a restoration image obtained by restoring a region concealed with the dirt in the latest capture image, the first learned model being a result obtained by machine learning a relationship between a first learning image in which learning dirt is not present and first learning dirt images each of which is made by causing the learning dirt to be present in the first learning image.
    Type: Grant
    Filed: November 7, 2019
    Date of Patent: July 19, 2022
    Assignee: AISIN CORPORATION
    Inventors: Yoshihito Kokubo, Yoshihisa Suetsugu
  • Patent number: 11359911
    Abstract: An abrasion inspection apparatus includes: a first imaging unit that is installed on a side of a track, a vehicle traveling along the track, a guide wheel being installed on a side of the vehicle, the first imaging unit imaging an inside of the track via a telecentric lens; a second imaging unit that is installed in a vehicle traveling direction with respect to the first imaging unit on the side of the track and images the inside of the track via a telecentric lens; an image acquisition unit that acquires an image which is an image of a boundary of the guide wheel captured by the first imaging unit and is an image of a boundary on a first direction side in the vehicle traveling direction and an image which is an image of the boundary of the guide wheel captured by the second imaging unit at the same time as the capturing of the image by the first imaging unit and is an image of a boundary on an opposite side to the first direction side; and a guide wheel detection unit that detects an abrasion situation of th
    Type: Grant
    Filed: September 19, 2019
    Date of Patent: June 14, 2022
    Assignee: MITSUBISHI HEAVY INDUSTRIES, LTD.
    Inventors: Katsuaki Morita, Masahiro Yamada, Kazuki Ozaki, Hiroyuki Kono
  • Patent number: 11354902
    Abstract: A method can include classifying, using a compressed and specialized convolutional neural network (CNN), an object of a video frame into classes, clustering the object based on a distance of a feature vector of the object to a feature vector of a centroid object of the cluster, storing top-k classes, a centroid identification, and a cluster identification, in response to receiving a query for objects of class X from a specific video stream, retrieving image data for each centroid of each cluster that includes the class X as one of the top-k classes, classifying, using a ground truth CNN (GT-CNN), the retrieved image data for each centroid, and for each centroid determined to be classified as a member of the class X providing image data for each object in each cluster associated with the centroid.
    Type: Grant
    Filed: May 15, 2020
    Date of Patent: June 7, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ganesh Ananthanarayanan, Paramvir Bahl, Peter Bodik, Tsuwang Hsieh, Matthai Philipose
  • Patent number: 11347962
    Abstract: The disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm, and application thereof. In particular, an electronic apparatus according to the disclosure includes a memory storing a trained artificial intelligence model, and a processor configured to acquire a plurality of feature values by inputting an input image to the artificial intelligence model. The trained artificial intelligence model applies each of a plurality of filters to a plurality of feature maps extracted from the input image and includes a pooling layer for acquiring feature values for the plurality of feature maps to which each of the plurality of filters is applied.
    Type: Grant
    Filed: July 11, 2019
    Date of Patent: May 31, 2022
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Bongjoe Kim
  • Patent number: 11348330
    Abstract: Systems, methods, and computer-executable instructions for extracting key value data. Optical character recognition (OCR) text of a document is received. The y-coordinate of characters are adjusted to a common y-coordinate. The rows of OCR text are tokenized into tokens based on a distance between characters. The tokens are ordered based on the x,y coordinates of the characters. The document is clustered into a cluster based on the ordered tokens and ordered tokens from other documents. Keys for the cluster are determined from the first set of documents. Each key is a token from a first set of documents. A value is assigned to each kay based on the tokens for the document, and values are assigned to each key for the other documents. The values for the document and the values for the other documents are stored in an output document.
    Type: Grant
    Filed: June 9, 2020
    Date of Patent: May 31, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventor: Nicolae Duta
  • Patent number: 11341635
    Abstract: Embodiments of the present disclosure include a method, device and computer readable medium involving receiving image data to detect tissue lesions, passing the image data through at least one first convoluted neural network, segmenting the image data, fusing the segmented image data, and detecting tissue lesions.
    Type: Grant
    Filed: October 31, 2019
    Date of Patent: May 24, 2022
    Assignee: TENCENT AMERICA LLC
    Inventor: Hanbo Chen
  • Patent number: 11335084
    Abstract: One embodiment provides a method, including: receiving, at an information handling device, drawing input; identifying, using a processor, at least one object in the drawing input; determining, based on the identifying, whether a factual anomaly exists in the drawing input with respect to the at least one object; and notifying, responsive to determining that a factual anomaly exists, a user of the factual anomaly.
    Type: Grant
    Filed: September 18, 2019
    Date of Patent: May 17, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ghulam Ahmed Ansari, Amrita Saha, Srikanth Govindaraj Tamilselvam
  • Patent number: 11321835
    Abstract: A method, a non-transitory computer readable medium and a system for determining three dimensional (3D) information of structural elements of a substrate.
    Type: Grant
    Filed: March 17, 2020
    Date of Patent: May 3, 2022
    Assignee: APPLIED MATERIALS ISRAEL LTD.
    Inventors: Anna Levant, Rafael Bistritzer
  • Patent number: 11244446
    Abstract: The present disclosure relates to systems and methods for imaging. The method may include obtaining a real-time representation of a subject. The method may also include determining at least one scanning parameter associated with the subject by automatically processing the representation according to a parameter obtaining model. The method may further include performing a scan on the subject based at least in part on the at least one scanning parameter.
    Type: Grant
    Filed: October 25, 2019
    Date of Patent: February 8, 2022
    Assignee: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.
    Inventors: Ziyan Wu, Shanhui Sun, Arun Innanje
  • Patent number: 11232572
    Abstract: A system and method are disclosed for segmenting a set of two-dimensional CT slices corresponding to a lesion. In an embodiment, for each of at least a subset of the set of CT slices, the system inputs the CT slice into a plurality of branches of a trained segmentation block. Each branch of the segmentation block includes a convolutional neural network (CNN) with filters at a different scale, and produces one or more levels of output. The system generates, for each CT slice in the subset, feature maps for each level of output. The system generates a segmentation of each CT slice in the subset based on the feature maps of each level of output. The system aggregates the segmentations of each slice in the subset to generate a three-dimensional segmentation of the lesion. The system transmits data representing the three-dimensional segmentation to a user interface for display.
    Type: Grant
    Filed: April 14, 2020
    Date of Patent: January 25, 2022
    Assignee: Merck Sharp & Dohme Corp.
    Inventors: Antong Chen, Gregory Goldmacher, Bo Zhou
  • Patent number: 11222226
    Abstract: A monitoring-screen-data generation device includes an object-data generation unit, a screen-data generation unit, and an assignment processing unit. The object-data generation unit identifies a plurality of objects included in an image based on image data, and generates object data. The screen-data generation unit generates monitoring screen data on the basis of the object data. On the basis of definition data that defines a state transition and the object data, the assignment processing unit assigns data that defines the state transition to an image object included in a monitoring screen of the monitoring screen data.
    Type: Grant
    Filed: March 21, 2017
    Date of Patent: January 11, 2022
    Assignee: MITSUBISHI ELECTRIC CORPORATION
    Inventor: Shingo Sodenaga
  • Patent number: 11213247
    Abstract: An image processing system, comprising an input interface (IN) for receiving a plurality of input images acquired of test objects. The system further comprises a material type analyzer (MTA) configured to produce material type readings at corresponding locations across said input images (IM(CH)). A statistical module (SM) of the system is configured to determine based on said readings an estimate for a probability distribution of material type for said corresponding locations.
    Type: Grant
    Filed: June 29, 2017
    Date of Patent: January 4, 2022
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Dominik Benjamin Kutra, Thomas Buelow, Joerg Sabczynski, Kirsten Regina Meetz
  • Patent number: 11210494
    Abstract: Method and apparatus for segmenting a cellular image are disclosed. A specific embodiment of the method includes: acquiring a cellular image; enhancing the cellular image using a generative adversarial network to obtain an enhanced cellular image; and segmenting the enhanced cellular image using a hierarchical fully convolutional network for image segmentation to obtain cytoplasm and zona pellucida areas in the cellular image.
    Type: Grant
    Filed: October 22, 2019
    Date of Patent: December 28, 2021
    Assignee: The Chinese University of Hong Kong
    Inventors: Yiu Leung Chan, Mingpeng Zhao, Han Hui Li, Tin Chiu Li
  • Patent number: 11200668
    Abstract: Method and system for grading a tumor. For example, a system for grading a tumor comprising: an image obtaining module configured to obtain a pathological image of a tissue to be examined; a snippet obtaining module configured to obtain one or more snippets having one or more sizes from the pathological image; an analyzing module configured to obtain one or more classification features based on at least analyzing the one or more snippets using one or more selected trained detection models of the analyzing module, wherein each selected trained detection model is configured to identify one or more classification features; and an outputting module configured to determine a tumor identification result based on at least the one or more classification features and output the tumor identification result.
    Type: Grant
    Filed: October 18, 2019
    Date of Patent: December 14, 2021
    Assignee: Shanghai United Imaging Intelligence Co., Ltd.
    Inventors: Qiuping Chun, Feng Shi, Yiqiang Zhan
  • Patent number: 11195040
    Abstract: A monitoring-screen-data generation device includes an object-data generation unit, a screen-data generation unit, and an assignment processing unit. The object-data generation unit identifies a plurality of objects included in an image based on image data, and generates object data. The screen-data generation unit generates monitoring screen data on the basis of the object data. On the basis of definition data that defines a state transition and the object data, the assignment processing unit assigns data that defines the state transition to an image object included in a monitoring screen of the monitoring screen data.
    Type: Grant
    Filed: March 21, 2017
    Date of Patent: December 7, 2021
    Assignee: MITSUBISHI ELECTRIC CORPORATION
    Inventor: Shingo Sodenaga
  • Patent number: 11170502
    Abstract: Provided is a method based on deep neural network to extract appearance and geometry features for pulmonary textures classification, which belongs to the technical fields of medical image processing and computer vision. Taking 217 pulmonary computed tomography images as original data, several groups of datasets are generated through a preprocessing procedure. Each group includes a CT image patch, a corresponding image patch containing geometry information and a ground-truth label. A dual-branch residual network is constructed, including two branches separately takes CT image patches and corresponding image patches containing geometry information as input. Appearance and geometry information of pulmonary textures are learnt by the dual-branch residual network, and then they are fused to achieve high accuracy for pulmonary texture classification. Besides, the proposed network architecture is clear, easy to be constructed and implemented.
    Type: Grant
    Filed: January 7, 2019
    Date of Patent: November 9, 2021
    Assignee: DALIAN UNIVERSITY OF TECHNOLOGY
    Inventors: Rui Xu, Xinchen Ye, Lin Lin, Haojie Li, Xin Fan, Zhongxuan Luo
  • Patent number: 11164312
    Abstract: A system associated with quantifying a density level of tumor-infiltrating lymphocytes, based on prediction of reconstructed TIL information associated with tumoral tissue image data during pathology analysis of the tissue image data is disclosed. The system receives digitized diagnostic and stained whole-slide image data related to tissue of a particular type of tumoral data. Defined are regions of interest that represents a portion of, or a full image of the whole-slide image data. The image data is encoded into segmented data portions based on convolutional autoencoding of objects associated with the collection of image data. The density of tumor-infiltrating lymphocytes is determined of bounded segmented data portions for respective classification of the regions of interest. A classification label is assigned to the regions of interest. It is determined whether an assigned classification label is above a pre-determined threshold probability value of lymphocyte infiltrated.
    Type: Grant
    Filed: November 30, 2018
    Date of Patent: November 2, 2021
    Assignees: The Research Foundation tor the State University of New York, Board of Regents, The University of Texas System, Institute for Systems Biology
    Inventors: Joel Haskin Saltz, Tahsin Kurc, Rajarsi Gupta, Tianhao Zhao, Rebecca Batiste, Le Hou, Vu Nguyen, Dimitrios Samaras, Arvind Rao, John Van Arnam, Pankaj Singh, Alexander Lazar, Ashish Sharma, Ilya Shmulevich, Vesteinn Thorsson
  • Patent number: 11138423
    Abstract: Arbitrary image data may be transformed into data suitable for optical character recognition (OCR) processing. A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate at least one text proposal using a region proposal network (RPN). The at least one text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may merge the text proposals with one another to form a patch of the image that is predicted to contain text. The processor may determine outer coordinates of the patch. The outer coordinates may comprise at least leftmost, rightmost, topmost, and bottommost coordinates. The processor may generate a quadrilateral of the image that is a smallest quadrilateral including the leftmost, rightmost, topmost, and bottommost coordinates.
    Type: Grant
    Filed: July 29, 2019
    Date of Patent: October 5, 2021
    Assignee: Intuit Inc.
    Inventors: Terrence J. Torres, Homa Foroughi