Patents Examined by Vikkram Bali
  • Patent number: 10810731
    Abstract: Disclosed are methods and systems that include obtaining at least one image of a dendritic structure, analyzing the at least one image to identify one or more features associated with the dendritic structure, and determining a numerical value associated with the dendritic structure based on the one or more features.
    Type: Grant
    Filed: November 6, 2015
    Date of Patent: October 20, 2020
    Assignee: Arizona Board of Regents on behalf of Arizona State University
    Inventor: Michael N. Kozicki
  • Patent number: 10809635
    Abstract: A defect inspection method and a defect inspection system are provided. In the method, a plurality of candidate defect images are retrieved from inspection images obtained by at least one optical inspection tool performing hot scans on at least one wafer and a plurality of attributes are extracted from the inspection images. A random forest classifier including a plurality of decision trees for classifying the candidate defect images is created, wherein the decision trees are built with different subset of the attributes and the candidate defect images. A plurality of candidate defect images are retrieved from the optical inspection tool in runtime and applied to the decision trees, and classified into nuisance images and real defect images according to votes of the decision trees in which the nuisance images are filtered out. The real defect images with the votes over a confidence value are sampled for microscopic review.
    Type: Grant
    Filed: March 29, 2018
    Date of Patent: October 20, 2020
    Assignee: Taiwan Semiconductor Manufacturing Company, Ltd.
    Inventors: Chien-Huei Chen, Hung-Yi Chung, Chao-Ting Hong, Cheng-Kuang Lee, Xiaomeng Chen, Teng-Cheng Hsu
  • Patent number: 10803360
    Abstract: A method for learning a neural network performed by a computing means wherein the neural network receives a marine image and outputs information about a type and a distance of at least one object included in the marine image is provided. The method comprises: obtaining a marine image including a sea and an obstacle; obtaining a labelling data generated based on the marine image; obtaining an output data by using a neural network, wherein the neural network receives the marine image and outputs the output data; calculating an error value by using the labelling data and the output data; and updating the neural network based on the error value; wherein the labelling data and the output data are determined by a combination of information about a type and a distance of an object.
    Type: Grant
    Filed: August 30, 2019
    Date of Patent: October 13, 2020
    Assignee: Seadronix Corp.
    Inventors: Byeol Teo Park, Han Keun Kim, Dong Hoon Kim
  • Patent number: 10803338
    Abstract: A method and apparatus for recognizing a character area in an image are provided. A specific embodiment of the method comprises: acquiring color values and position information of pixel points in a to-be-recognized image; clustering the pixel points based on the color values of the pixel points, the color values of the pixel points in each pixel point category being identical or similar; determining, for each category of clustered pixel points, outlines of connected regions including the pixel points in each category of pixel points, to obtain an outline set; and merging, based on the color values and the position information of the outlines in the outline set, the outlines, to obtain character areas in the image. The embodiment has improved the accuracy of recognizing character lines in recognizing characters in an image.
    Type: Grant
    Filed: October 15, 2018
    Date of Patent: October 13, 2020
    Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Xin Chen, Jianzhong Gao, Chengjun Lei, Dongxue Wu, Linlin Yang, Taoyuan Cheng
  • Patent number: 10796422
    Abstract: A system and method allows a light colored image of an object such as a check to be detected and captured on a light colored background for uploading to a server for processing. Detection involves detecting edges of objects on the image, drawing a rectangle around the detected edges, testing for an aspect ratio of the rectangle within an approved range, testing for the rectangle being outside of a margin of the image and being a certain percentage of the image, and testing for blur within a tolerable range.
    Type: Grant
    Filed: May 31, 2018
    Date of Patent: October 6, 2020
    Assignee: Charles Schwab & Co., Inc.
    Inventor: Amy L. Acuff
  • Patent number: 10789687
    Abstract: In an image processing method that converts image data into output data by performing tone mapping, an edge of an image represented by the image data is determined, a first tone mapping operation is performed on first image data included in the image data, where the first image data represent a first portion of the image not including the edge, whether a gray level of second image data is within a predetermined gray range is determined, where the second image data represent a second portion of the image including the edge, a second tone mapping operation is performed on the second image data when the gray level of the second image data is within the gray range, and the first tone mapping operation is performed on the second image data when the gray level of the second image data is not within the gray range.
    Type: Grant
    Filed: November 14, 2018
    Date of Patent: September 29, 2020
    Assignee: SAMSUNG DISPLAY CO., LTD.
    Inventors: Nam-Gon Choi, Namjae Lim, Moonshik Kang, Jinpil Kim, JaeSung Bae, Jaehoon Lee
  • Patent number: 10776962
    Abstract: A system and method are provided for the reconstruction of medical image data using filtered backprojection with the use of a wavelet transformation. A filter function is applied to at least one part of an object using projection data captured with a detection device prior to backprojection.
    Type: Grant
    Filed: May 8, 2017
    Date of Patent: September 15, 2020
    Assignee: Siemens Healthcare GmbH
    Inventors: Sebastian Bauer, Andreas Maier, Yan Xia
  • Patent number: 10776933
    Abstract: This disclosure provides enhanced techniques for tracking the movement of real-world objects for improved display of virtual objects that are associated with the real-world objects. A first device can track the position of a real-world object. When the real-world object moves out of a viewing area of the first device, a second device can use metadata defining physical characteristics of the real-world object shared by the first device to identify the real-world object as the real-world object comes into a viewing area of the second device. The second device can then maintain an association between the real-world object and the virtual objects as the real-world object moves, and share such information with other computers to enable the other computers to display the virtual objects in association with the real-world object even though they are not in direct view of an associated real-world object.
    Type: Grant
    Filed: December 6, 2018
    Date of Patent: September 15, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventor: Jason Thomas Faulkner
  • Patent number: 10769493
    Abstract: The embodiments of the present invention provide training and construction methods and apparatus of a neural network for object detection, an object detection method and apparatus based on a neural network and a neural network. The training method of the neural network for object detection, comprises: inputting a training image including a training object to the neural network to obtain a predicted bounding box of the training object; acquiring a first loss function according to a ratio of the intersection area to the union area of the predicted bounding box and a true bounding box, the true bounding box being a bounding box of the training object marked in advance in the training image; and adjusting parameters of the neural network by utilizing at least the first loss function to train the neural network.
    Type: Grant
    Filed: July 26, 2017
    Date of Patent: September 8, 2020
    Assignees: BEIJING KUANGSHI TECHNOLOGY CO., LTD., MEGVII (BEIJING) TECHNOLOGY CO., LTD.
    Inventors: Jiahui Yu, Qi Yin
  • Patent number: 10752158
    Abstract: A pulsed laser may illuminate a scene that is obscured by dense, dynamic and heterogeneous fog. Light may reflect back to a time-resolved camera. Each pixel of the camera may detect a single photon during each frame. The imaging system may accurately determine reflectance and depth of the fog-obscured target, without any calibration or prior knowledge of the scene depth. The imaging system may perform a probabilistic algorithm that exploits the fact that times of arrival of photons reflected from fog have a Gamma distribution that is different than the Gaussian distribution of times of arrival of photons reflected from the target. The probabilistic algorithm may take into account times of arrival of all types of measured photons, including scattered and un-scattered photons.
    Type: Grant
    Filed: February 7, 2019
    Date of Patent: August 25, 2020
    Assignee: Massachusetts Institute of Technology
    Inventors: Guy Satat, Matthew Tancik, Ramesh Raskar
  • Patent number: 10755069
    Abstract: Inspired by Shack Hartmann Wavefront Patterns, a device may obtain three dimensional images for use in authentication. Since such images can have high resolution, damage in, for instance, skin on a finger may be recorded and used as part of a temporary template image. In future authentication attempts, an aged version of the temporary template image may be used. Additionally, reference points on the damage may be employed when authenticating.
    Type: Grant
    Filed: November 21, 2018
    Date of Patent: August 25, 2020
    Assignee: BlackBerry Limited
    Inventors: Peter Mankowski, Adam Sosnowski, Krzysztof Zawada
  • Patent number: 10755413
    Abstract: This disclosure generally pertains to methods and systems for processing electronic data obtained from imaging or other diagnostic and evaluative medical procedures. Certain embodiments relate to methods for the development of deep learning algorithms that perform machine recognition of specific features and conditions in imaging and other medical data. Another embodiment provides systems configured to detect and localize medical abnormalities on medical imaging scans by a deep learning algorithm.
    Type: Grant
    Filed: February 24, 2020
    Date of Patent: August 25, 2020
    Assignee: Qure.AI Technologies Private Limited
    Inventors: Preetham Putha, Manoj Tadepalli, Bhargava Reddy, Tarun Raj, Ammar Jagirdar, Pooja Rao, Prashant Warier
  • Patent number: 10740611
    Abstract: An state determination system comprises an information acquiring portion that acquires an environment information, a movable body, an instruction portion that performs an action instruction to the movable body, and an estimation portion that estimates an abnormality of the object based on at least one of the information acquired by the information acquiring portion and the environment information acquired by the movable body. In case the estimation portion estimates the abnormality of the object, the instruction portion performs the action instruction for moving to the neighborhood of the object and requiring a response, to the movable body. At least one of the information acquiring portion and the movable body acquires the response state of the object to the action of the movable body instructed by the instruction portion. The state determination system comprises a determination portion that the abnormality of the object based on the acquired response state.
    Type: Grant
    Filed: December 19, 2014
    Date of Patent: August 11, 2020
    Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
    Inventor: Fuminori Saito
  • Patent number: 10733485
    Abstract: A writing preservation apparatus preserves, as image data, writing on a writing target medium in which writing is performed and erasing of writing in an arbitrary region is performed. The apparatus includes an acquisition unit that acquires time-series image data items at points of times for the writing target medium, a written region recognition unit that recognizes written regions in which writing is performed on the writing target medium at the points of time based on the image data items at the points of time which are acquired by the acquisition unit, and a preservation unit that preserves first image data at a first point of time in a case where the written region recognized based on the first image data in whole or part is absent in the written region recognized based on second image data at a second point of time subsequent to the first point of time.
    Type: Grant
    Filed: November 7, 2017
    Date of Patent: August 4, 2020
    Assignee: FUJI XEROX CO., LTD.
    Inventor: Kohshiro Inomata
  • Patent number: 10733459
    Abstract: An image processing device includes: a generating unit that generates, based on a distance image, two-dimensional distribution information indicating a two-dimensional distribution of an object, in which a distance in a horizontal direction, a distance in a depth direction, and a frequency value corresponding to the distances are related; and a labeling unit that conducts a labeling process by conducting search on the two-dimensional distribution information multiple times, detecting a pixel having the frequency value that is more than a predetermined threshold during each search, and assigning a label that is different in each times of search, wherein the labeling unit conducts a first labeling process by selecting a pixel having the frequency value that is more than the threshold from pixels that abut a pixel being searched in a search direction and assigning the label when the label is not assigned to the pixel selected.
    Type: Grant
    Filed: September 10, 2018
    Date of Patent: August 4, 2020
    Assignee: RICOH COMPANY, LTD.
    Inventors: Yuu Yamada, Soichiro Yokota, Sadao Takahashi, Shinichi Sumiyoshi
  • Patent number: 10735728
    Abstract: Disclosed are a method for processing an image and an apparatus therefor. Specifically, a method for decoding an image comprises: a step of deriving an initial block size information indicating information in which a first block, which is a basic unit for dividing an image, is divided into one or more initial blocks; a step of deriving a division information indicating information in which the initial block is divided into a plurality of second blocks in the initial block unit divided from the first block based on the initial block size information; and a step of decoding in a second block unit recursively divided from the initial block based on the division information.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: August 4, 2020
    Assignee: LG ELECTRONICS INC.
    Inventors: Jungdong Seo, Jaehyun Lim, Naeri Park
  • Patent number: 10722191
    Abstract: A method for diagnosis and evaluation of tooth decay comprises: locating in an x-ray image the contour of the dento-enamel junction (DEJ); measuring optical density along contours substantially parallel to and on either side of the DEJ contour; and calculating at least one decay value from the measured optical densities. A method for diagnosis and evaluation of periodontal disease comprises: measuring in an x-ray image a bone depth (BD) relative to the position of the cemento-enamel junctions (CEJs) of adjacent teeth; measuring bone density along a contour between the adjacent teeth; and calculating a crestal density (CD) value from the measured bone density. Calibration standards may be employed for facilitating calculation of the values. A dental digital x-ray imaging calibration method for at least partly correcting for variations of the optical densities of images acquired from the dental digital x-ray imaging system.
    Type: Grant
    Filed: December 1, 2017
    Date of Patent: July 28, 2020
    Assignee: OREGON DENTAL, INC.
    Inventor: Leigh E. Colby
  • Patent number: 10726230
    Abstract: There is disclosed a display panel and its driving method and a display device in the technical field of display. The display panel according to the disclosure includes a base substrate, a driving structure provided on the base substrate, a receiving structure provided above the driving structure, and a fingerprint detection module provided on the base substrate, wherein the driving structure is configured to create an ultrasonic signal, the receiving structure is configured to receive the ultrasonic signal reflected from a finger and transform the reflected ultrasonic signal into an electric signal which is input to the fingerprint detection module, and the fingerprint detection module is configured to determine fingerprint information from the electric signal output by the receiving structure.
    Type: Grant
    Filed: September 30, 2017
    Date of Patent: July 28, 2020
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Yingming Liu, Xue Dong, Haisheng Wang, Xiaoliang Ding, Rui Xu, Lijun Zhao
  • Patent number: 10701999
    Abstract: Images can be used to determine the size of an article of clothing matching the physical characteristics of a user. An image can include an article of clothing known to fit well or a representation of a body part, which can comprise the body part itself. Images can also include a reference item. Various techniques are used to determine one or more perspective distortions in the image based on analysis of the reference item and information known about the reference item. The one or more perspective distortions can be accounted for to determine physical characteristics of the article of clothing or the body part associated with the article of clothing. The physical characteristics can be used to determine the size of an article of clothing matching, or corresponding to, the physical characteristics.
    Type: Grant
    Filed: December 17, 2015
    Date of Patent: July 7, 2020
    Assignee: A9.COM, INC.
    Inventors: Eran Borenstein, Chetan Pitambar Bhole, Erick Cantu-Paz, Arnab Sanat Kumar Dhua, Anish Ramdas Nair
  • Patent number: 10706257
    Abstract: Method for detecting attempted fraud by using an artificial material during a biometric acquisition, including: illuminating, with lighting, a surface of an object having a texture, acquiring a first image of the surface; illuminating, with non-uniform lighting, the surface and acquiring a second image of the surface, the non-uniform lighting causing light to diffuse within the illuminated material at an intensity that varies according to a law that is a function of a first position parameter and is invariable along a second position parameter; computing a correction, varying along the first position parameter, that is to be locally applied to the first image to bring the amplitude of the texture on the first image substantially to the level of that on the second image; generating, on the basis of the correction, information relating to the artificial or non-artificial nature of the material.
    Type: Grant
    Filed: June 7, 2018
    Date of Patent: July 7, 2020
    Assignee: IDEMIA IDENTITY & SECURITY FRANCE
    Inventor: Jean Beaudet