Patents Examined by Daniel G. Mariam
  • Patent number: 10789737
    Abstract: A computer implemented method for reconstructing a 3-D volume image using a radiographic imaging system having one or more x-ray sources and a digital detector. A plurality of radiographic images of a subject at various angles are captured in the digital detector. Image data in two or more pixels of the detector that are adjacent to each other in a row direction or a column direction are combined, while pixels adjacent in the other direction are not combined.
    Type: Grant
    Filed: December 20, 2016
    Date of Patent: September 29, 2020
    Assignee: Carestream Health, Inc.
    Inventors: Xiaohui Wang, Richard A. Simon, Levon O. Vogelsang, Nathan J. Packard
  • Patent number: 10776652
    Abstract: Described herein are systems and methods that use motion-related data combined with image data to improve the speed and the accuracy of detecting visual features by predict the locations of features using the motion-related data. In embodiments, given a set of features in a previous image frame and given a next image frame, localization of the same set of features in the next image frame is attempted. In embodiments, motion-related data is used to compute the relative pose transformation between the two image frames, and the image location of the features may then be transformed to obtain their location prediction in the next frame. Such a process greatly reduces the search space of the features in the next image frame, and thereby accelerates and improves feature detection.
    Type: Grant
    Filed: August 13, 2018
    Date of Patent: September 15, 2020
    Assignee: Baidu USA LLC
    Inventors: Yingze Bao, Mingyu Chen
  • Patent number: 10769766
    Abstract: Aspects of the present disclosure relate to machine learning techniques for training a model to identify each of a number of different classes in images, based on training data where each training image may not be labeled in a complete manner with respect to the classes. The disclosed training techniques use a new label value to indicate when a ground truth value is unknown for a particular class, and do not penalize the machine learning network for output predictions that do not match the label value representing unknown ground truth. Some implementations of the training process can be regularized to impose sparsity on predicted classes in order to avoid false positive predictions.
    Type: Grant
    Filed: May 31, 2018
    Date of Patent: September 8, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Dirk Padfield, Suren Kumar
  • Patent number: 10769749
    Abstract: A processor includes: a first memory configured to store image data including pixel data of a plurality of pixels that are two-dimensionally arranged; a second memory configured to store neighborhood matrix image data including pixel data of a neighborhood matrix; and a format converter that includes (a) a readout circuit configured to read out the image data from the first memory, (b) a padding arithmetic unit configured to receive the read-out image data, select pixel data of the received read-out image data and padding data inserted at periphery of the plurality of pixels in accordance with mask values of a padding mask, and generate the neighborhood matrix image data including the pixel data and the padding data, and (c) a writing circuit configured to write the neighborhood matrix image data to the second memory.
    Type: Grant
    Filed: February 28, 2019
    Date of Patent: September 8, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Katsuhiro Yoda, Mitsuru Tomono, Takahiro Notsu
  • Patent number: 10769794
    Abstract: A method of object detection includes obtaining a set of images depicting overlapping regions of an area containing a plurality of objects. Each image includes input object indicators defined by input bounding boxes, input confidence level values, and object identifiers. The method includes identifying candidate subsets of input object indicators in adjacent images. Each candidate subset has input overlapping bounding boxes in a common frame of reference, and a common object identifier. The method includes adjusting the input confidence levels for each input object indicator in the candidate subsets; selecting clusters of the input object indicators satisfying a minimum input confidence threshold, having a common object identifier, and having a degree of overlap satisfying a predefined threshold; and detecting an object by generating a single output object indicator for each cluster, the output object indicator having an output bounding box, an output confidence level value, and the common object identifier.
    Type: Grant
    Filed: November 22, 2019
    Date of Patent: September 8, 2020
    Assignee: Symbol Technologies, LLC
    Inventors: Joseph Lam, Xinyi Gong
  • Patent number: 10769462
    Abstract: An information processing apparatus includes a position specifying unit that specifies a position of each member of an assembly, a biometric information acquiring unit that acquires biometric information from members of which the number is smaller than the number of all members, an activeness degree specifying unit that specifies, from the biometric information acquired by the biometric information acquiring unit, an activeness degree of the member from which the biometric information is acquired by the biometric information acquiring unit, and specifies, from the activeness degree and the position specified by the position specifying unit, an activeness degree of a member other than the member from which the biometric information is acquired by the biometric information acquiring unit among the members, and a determination unit that determines a state of the assembly from the activeness degree specified by the activeness degree specifying unit.
    Type: Grant
    Filed: August 13, 2018
    Date of Patent: September 8, 2020
    Assignee: FUJI XEROX CO., LTD.
    Inventor: Shoko Chiba
  • Patent number: 10769425
    Abstract: A method of determining a hierarchy of a blank template using an image of the blank template and using the determined hierarchy for providing labels and field values of text lines of a filled form document.
    Type: Grant
    Filed: August 13, 2018
    Date of Patent: September 8, 2020
    Assignee: International Business Machines Corporation
    Inventors: Antonio Foncubierta Rodriguez, Maria Gabrani, Guillaume Jaume
  • Patent number: 10755447
    Abstract: Makeup identification using deep learning in a digital medium environment is described. Initially, a user input is received to provide a digital image depicting a face which has a desired makeup characteristic. A discriminative neural network is trained to identify and describe makeup characteristics of the input digital image based on data describing differences in visual characteristics between pairs of images, which include a first image depicting a face with makeup applied and a second image depicting a face without makeup applied. The makeup characteristics identified by the discriminative neural network are displayed for selection to search for similar digital images that have the selected makeup characteristic. Once retrieved, the similar digital images can be displayed along with the input digital image having the desired makeup characteristic.
    Type: Grant
    Filed: May 31, 2018
    Date of Patent: August 25, 2020
    Assignee: Adobe Inc.
    Inventors: Niyati Himanshu Chhaya, Nitin Rathor, Lilly Kumari, Vineet Vinayak Pasupulety, Rutuj Jugade
  • Patent number: 10748019
    Abstract: An image processing method and an electronic apparatus for foreground image extraction include steps: (A) acquiring frame images of a dynamic image, wherein each frame image has an RGB image and an IR image; (B) acquiring an RGB image representing a dark state as an RGB capture image, acquiring an IR image representing a light state as an IR light frame image, and acquiring one IR image representing the dark state as an IR dark frame image; (C) calculating a difference image between the IR light frame image and the IR dark frame image and binarizing the difference image to generate a binarized image; and (D) acquiring a plurality of foreground pixels corresponding to an IR foreground part of the binarized image of the RGB capture image and taking the foreground pixels as the foreground image, thereby reducing the impact of ambient light, background noise and calculation.
    Type: Grant
    Filed: August 22, 2018
    Date of Patent: August 18, 2020
    Assignee: REALTEK SEMICONDUCTOR CORP.
    Inventors: Zhong-Yi Qiu, Wen-Tsung Huang, Kai Liu
  • Patent number: 10740919
    Abstract: A system for measuring a flushness of a fastener in a surface includes a plurality of lights configured to illuminate the fastener and the surface. The system also includes a camera configured to capture a plurality of images of the fastener and the surface while the lights sequentially illuminate the fastener and the surface. The system also includes a computing system configured to determine a normal map of the fastener and the surface based at least partially upon the images, determine a depth map of the fastener and the surface based at least partially upon the normal map, and determine the flushness of the fastener with respect to the surface based at least partially upon the depth map.
    Type: Grant
    Filed: November 13, 2018
    Date of Patent: August 11, 2020
    Assignee: THE BOEING COMPANY
    Inventors: Ben Rennison, Jonathan A. Cox, Jyani S. Vaddi, Christopher A. Greer
  • Patent number: 10726948
    Abstract: Medical imaging device- and display-invariant segmentation and measurement is provided. In various embodiments, a plurality of medical images is read from a data store. Metadata of each of the plurality of medical images is read. The metadata identifies an image acquisition device associated with each of the plurality of medical images. Based on the plurality of medical images and the metadata of each of the plurality of images, a learning system is trained to determine one or more image correction parameters. The one or more image correction parameters optimize segmentation of the plurality of medical images.
    Type: Grant
    Filed: December 8, 2017
    Date of Patent: July 28, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Mark D. Bronkalla, Sun Young Park, Murray A. Reicher, Dustin Sargent
  • Patent number: 10719728
    Abstract: A method for controlling an infrared fill light and related products are provided, and the method includes the follows. A reference biometric recognition pattern that is used by a mobile terminal to process a target event is obtained. A target fill-light strategy corresponding to the reference biometric recognition pattern is determined according to a pre-stored mapping relationship between biometric recognition patterns and fill-light strategies of the infrared fill light. The infrared fill light is controlled to fill light according to the target fill-light strategy when the reference biometric recognition pattern is enabled.
    Type: Grant
    Filed: July 11, 2018
    Date of Patent: July 21, 2020
    Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.
    Inventors: Haiping Zhang, Yibao Zhou
  • Patent number: 10719741
    Abstract: Disclosed is a sensory information providing apparatus. The sensory information providing apparatus may comprise a learning model database storing a plurality of learning models related to sensory effect information with respect to a plurality of videos; and a video analysis engine generating the plurality of learning models by extracting sensory effect association information by analyzing the plurality of videos and sensory effect meta information of the plurality of videos, and extracting sensory information corresponding to an input video stream by analyzing the input video stream based on the plurality of learning model.
    Type: Grant
    Filed: February 6, 2018
    Date of Patent: July 21, 2020
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Noh Sam Park, Hoon Ki Lee, Mi Kyong Han
  • Patent number: 10713778
    Abstract: A semiconductor defect classification device includes feature extractors that are configured to receive images of semiconductor patterns on a wafer and to extract features of the images from the images, and a classifier that is configured to receive the features of the images and first meta information about the wafer and to use machine learning to classify a defect of the semiconductor patterns associated with the images based on the features of the images and the first meta information.
    Type: Grant
    Filed: July 11, 2018
    Date of Patent: July 14, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Namyeong Kwon, Hyohyeong Kang, Yongdeok Kim
  • Patent number: 10713522
    Abstract: A method for analyzing images to generate a plurality of output features includes receiving input features of the image and performing Fourier transforms on each input feature. Kernels having coefficients of a plurality of trained features are received and on-the-fly Fourier transforms (OTF-FTs) are performed on the coefficients in the kernels. The output of each Fourier transform and each OTF-FT are multiplied together to generate a plurality of products and each of the products are added to produce one sum for each output feature. Two-dimensional inverse Fourier transforms are performed on each sum.
    Type: Grant
    Filed: May 1, 2019
    Date of Patent: July 14, 2020
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Mihir Narendra Mody, Manu Mathew, Chaitanya Satish Ghone
  • Patent number: 10713569
    Abstract: System, methods, and other embodiments described herein relate to improving the generation of realistic images. In one embodiment, a method includes acquiring a synthetic image including identified labels of simulated components within the synthetic image. The synthetic image is a simulated visualization and the identified labels distinguish between the components within the synthetic image. The method includes computing, from the simulated components, translated components that visually approximate real instances of the simulated components by using a generative module comprised of neural networks that are configured to separately generate the translated components. The method includes blending the translated components together to produce a new image from the simulated components of the synthetic image.
    Type: Grant
    Filed: May 31, 2018
    Date of Patent: July 14, 2020
    Assignee: Toyota Research Institute, Inc.
    Inventors: German Ros Sanchez, Adrien D. Gaidon, Kuan-Hui Lee, Jie Li
  • Patent number: 10713528
    Abstract: A system for evaluating a user-marked document having a response area and at least one image marker, the system includes a means for receiving a digital image of the user-marked document and a computer to identify user-mark positional information of at least one user-mark within the response area relative to the at least one image marker from the received digital image.
    Type: Grant
    Filed: December 20, 2018
    Date of Patent: July 14, 2020
    Inventor: Daniel Kleinman
  • Patent number: 10706337
    Abstract: An multifunction peripheral includes a font dictionary data configured to include an italic font and a non-italic font for each character code, a determination method selection unit that selects, from a plurality of italic determination methods that are used for italic determination for the character, the italic determination method that is associated with the character code that has been acquired, an italic determination unit that determines whether or not the character in the image data is italic using the italic determination method that has been selected by the determination method selection unit, and a font specifying unit that specifies a font of the character by checking the character that has been determined to be italic by the italic determination unit only with the italic font and checking the character that has been determined to be non-italic only with the non-italic font.
    Type: Grant
    Filed: February 22, 2018
    Date of Patent: July 7, 2020
    Assignee: KYOCERA Document Solutions Inc.
    Inventor: Mineyuki Tsuda
  • Patent number: 10706284
    Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.
    Type: Grant
    Filed: August 20, 2019
    Date of Patent: July 7, 2020
    Assignee: AVIGILON PATENT HOLDING 1 CORPORATION
    Inventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
  • Patent number: 10708596
    Abstract: An encoder of a multimedia system encodes data representative of each image in a video stream to form a bitstream that is transmitted over a network to a decoder that decodes the bitstream and provides the decoded information to a multimedia application for display to the user. As consecutive images may have nearly identical pixel values, the multimedia system detects pixel value variations between consecutive images that are below a specified threshold to reduce active processing on such pictures, which includes, for example, encoding, decoding, and post-processing. The multimedia system either selectively encodes or selectively processes the current image that has pixel values that vary from an immediately preceding image within the specified threshold.
    Type: Grant
    Filed: November 20, 2017
    Date of Patent: July 7, 2020
    Assignee: ATI TECHNOLOGIES ULC
    Inventors: Ihab Amer, Fabio Gulino, Edward Harold, Boris Ivanovic, Haibo Liu, Ho Hin Lau, Gabor Sines, Catalin Beju