Patents Examined by Bhavesh M. Mehta
  • Patent number: 10628710
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. One of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.
    Type: Grant
    Filed: December 19, 2018
    Date of Patent: April 21, 2020
    Assignee: Google LLC
    Inventors: Sergey Ioffe, Corinna Cortes
  • Patent number: 10607101
    Abstract: Images in bitonal formats often include watermarks, stamps, or other patterns and artifacts. These patterned artifacts may be represented as a series of geometric points, dots, and/or dashes in the general shape of the original pattern. These patterned artifacts make other processes such as optical character recognition (OCR) difficult or impossible when items or pixels of interest are also found within the pattern of such artifact(s). Current patterned artifact removal solutions use methods of erosion to minimize the unwanted patterned artifact. However, such methods also erode the pixels/items of interest which, in turn, cause failures in other processes, such as OCR, that are desired to be carried out on or with the image.
    Type: Grant
    Filed: December 12, 2017
    Date of Patent: March 31, 2020
    Assignee: Revenue Management Solutions, LLC
    Inventor: Jay Wagner
  • Patent number: 10600182
    Abstract: An image processing apparatus includes an image obtaining unit configured to obtain a time-sequential image obtained in order of a start image, a plurality of intermediate images, and an end image, an image selecting unit configured to select a plurality of combinations of images including the start image, at least one of the plurality of intermediate images, and the end image, and a conformable image determining unit configured to determine a conformable combination from among the plurality of combinations based on image quality of the images included in each of the plurality of combinations and a similarity between the images included in each of the plurality of combinations.
    Type: Grant
    Filed: January 23, 2018
    Date of Patent: March 24, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventor: Keita Nakagomi
  • Patent number: 10599907
    Abstract: A display panel for fingerprint recognition and a display device are disclosed. The display panel for fingerprint recognition includes: a driving circuit backboard; a plurality of electroluminescent units disposed on the driving circuit backboard in a form of array; a plurality of infrared luminescent units disposed on the driving circuit backboard in a form of array; a protection cover plate; and a plurality of infrared photosensitive induction units disposed in a form of array between the protection cover plate and a film on which the infrared luminescent units are located.
    Type: Grant
    Filed: February 10, 2017
    Date of Patent: March 24, 2020
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Rui Xu, Xue Dong, Jing Lv, Haisheng Wang, Yingming Liu, Xiaoliang Ding, Changfeng Li, Yannan Jia, Lijun Zhao, Yuzhen Guo, Pengpeng Wang, Yanling Han, Wei Liu, Chun-Wei Wu
  • Patent number: 10595062
    Abstract: A method of encapsulating an encoded bitstream representing one or more images, the encapsulated bitstream comprising a data part and a metadata part. The method including providing image item information identifying a portion of the data part representing a sub-image or an image of a single image; providing image description information comprising parameters including display parameters and/or transformation operators relating to one or more images and outputting said bitstream together with said provided information as an encapsulated data file, wherein the image description information is stored in the metadata part.
    Type: Grant
    Filed: February 9, 2016
    Date of Patent: March 17, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventors: Frédéric Maze, Franck Denoual, Cyril Concolato, Jean Le Feuvre
  • Patent number: 10579868
    Abstract: A system for recognition of objects from ink elements on a computing device is provided. The computing device comprises a processor, a memory and at least one non-transitory computer readable medium for recognizing content under control of the processor. The at least one non-transitory computer readable medium is configured to determine a perimeter of an ink element stored in a memory of the computing device, determine a plurality of pen units for the ink element based on the determined ink element perimeter, determine at least one stroke representing a path through two or more of the pen units, and cause recognition of one or more objects represented by the ink element using the determined at least one stroke.
    Type: Grant
    Filed: September 11, 2017
    Date of Patent: March 3, 2020
    Assignee: MYSCRIPT
    Inventors: Thibault Lelore, Udit Roy
  • Patent number: 10572992
    Abstract: A method, apparatus and computer readable memory for solder paste inspection. A light source is configured to irradiate a sample solder joint comprising an organic material, an organic and metal material enclosed by an irregular boundary, and a metal material enclosed by a regular boundary. A first wavelength ultraviolet (UV) energy irradiates the sample to obtain first fluorescence energy, and a second wavelength UV energy irradiates the sample to obtain second fluorescence energy. A two-dimensional (2D) camera is configured to acquire a first image of the sample primarily from the first fluorescence energy and a second image of the sample primarily from the second fluorescence energy. Photo manipulation software is stored on at least one hardware processor, the photo manipulation software configured to overlay the first image and the second image to visually compare the boundary of the organic and metal material with the boundary of the metal material.
    Type: Grant
    Filed: December 28, 2017
    Date of Patent: February 25, 2020
    Assignee: Intel Corporation
    Inventors: Alireza Ashari, Curt Carboni, Jason Jones, Robert Wiedmaier, Di Xu, Wei Yan, Liang Zhang
  • Patent number: 10565724
    Abstract: A method for tracking a position of a device is provided, wherein the method includes capturing, at a first positional resolution, based on information from a first sensor, a first position of the device within an optical tracking zone of the first sensor. The method also includes determining, based on information from the first sensor, that the device exits the optical tracking zone of the first sensor. Further, the method includes responsive to determining that the device exits the optical tracking zone of the first sensor, capturing, at a second positional resolution, a second position of the device based on acceleration information from a second sensor, wherein the second positional resolution corresponds to a minimum threshold value for the acceleration information from the second sensor.
    Type: Grant
    Filed: December 26, 2017
    Date of Patent: February 18, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Christopher A. Peri
  • Patent number: 10567736
    Abstract: A three-dimensional object detection apparatus includes an input interface and a controller. The input interface accepts input of first and second images having mutual parallax in a first direction. The controller generates a parallax image that uses a pixel value to represent a difference in the first direction between positions of a subject in the first image and in the second image and divides the parallax image into a plurality of partial regions extending along a second direction. For each partial region, the controller segments a distance in the direction towards the subject into a plurality of distance intervals; and calculates, on the basis of a pixel count of pixels belonging to the distance interval, an evaluation value of a three-dimensional object belonging to the distance interval. The controller uses a different threshold for each distance interval to determine whether or not a three-dimensional object is present.
    Type: Grant
    Filed: June 23, 2016
    Date of Patent: February 18, 2020
    Assignee: KYOCERA Corporation
    Inventor: Tomofumi Koishi
  • Patent number: 10565462
    Abstract: In an electronic apparatus that captures images, characters in an image are accurately recognized. The electronic apparatus includes an imaging section, a distance measurement section, a shape estimation section, and a coordinate conversion section. The imaging section images an object and captures image data. The distance measurement section measures distances from the imaging section to a plurality of measurement points on a surface of the object. The shape estimation section estimates a shape of the object from the measured distances. The coordinate conversion section performs coordinate conversion on the image data, the coordinate conversion including converting three-dimensional coordinates on the surface of the object into plane coordinates on a predetermined reference plane on the basis of the estimated shape.
    Type: Grant
    Filed: February 28, 2017
    Date of Patent: February 18, 2020
    Assignee: Sony Corporation
    Inventors: Mitsuharu Ohki, Nobuki Furue, Yoshihito Ohki, Keisuke Touyama, Masahiro Watanabe, Kensei Jo
  • Patent number: 10558881
    Abstract: Provided is a parallax minimization stitching method and apparatus using control points in an overlapping region. A parallax minimization stitching method may include defining a plurality of control points in an overlapping region of a first image and a second image received from a plurality of cameras, performing a first geometric correction by applying a homography to the control points, defining a plurality of patches based on the control points, and performing a second geometric correction by mapping the patches.
    Type: Grant
    Filed: July 28, 2017
    Date of Patent: February 11, 2020
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Yong Ju Cho, Soon-heung Jung, Hyun Cheol Kim, Jeongil Seo, Joo Myoung Seok, Sangwoo Ahn, Seung Jun Yang, Injae Lee, Hee Kyung Lee, Seong Yong Lim
  • Patent number: 10559078
    Abstract: This disclosure provides a method for object detection. The method comprises receiving a user input that specifies one or more first regions and one or more second regions in a template image. The one or more second regions include one or more objects of interest. The method further comprises for each of the one or more first regions discovering a third region in an image under detection corresponding to the first region in the template image by matching the image under detection with the template image. The method further comprises computing a transformation function based on the matching from each of the one or more first regions to its corresponding third region. The method further comprises applying the computed transformation function to the one or more second regions to localize one or more fourth regions in the image under detection for the object detection.
    Type: Grant
    Filed: April 12, 2019
    Date of Patent: February 11, 2020
    Assignee: International Business Machines Corporation
    Inventors: Guo Qiang Hu, Jing Chang Huang, Jun Chi Yan, Jun Zhu
  • Patent number: 10552662
    Abstract: An optical identification method, includes: projecting light on a finger to generate reflected light from the finger; receiving the reflected light by a pixel sensing array to obtain a plurality of finger images; and determining whether the finger images present a liveness characteristic, according to a required exposure time or average brightness of the finger images obtained by the pixel sensing array. When the finger images present the liveness characteristic, the optical identification method further includes: determining identification information according to the finger images; or when the finger images do not present the liveness characteristic, the optical identification method further includes: not determining identification information according to the finger images, and optionally, stopping the pixel sensing array from obtaining a subsequent finger image.
    Type: Grant
    Filed: December 29, 2017
    Date of Patent: February 4, 2020
    Assignee: BEYOND TIME INVESTMENTS LIMITED
    Inventors: Chu-Hsin Chang, Jun-Shian Hsiao, Chun-Fu Lin, Hui-Min Tsai
  • Patent number: 10552696
    Abstract: An electronic device having a biometric sensor is provided. The electronic device includes a first region including a plurality of first pixels arranged in a first manner and a second region including a plurality of second pixels arranged in a second manner, a biometric sensor disposed in at least a part of the first region, and a processor electrically coupled with the display and the biometric sensor, and configured to receive a user input through the first region, and control the biometric sensor to detect biometric information corresponding to the user input.
    Type: Grant
    Filed: December 12, 2017
    Date of Patent: February 4, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Joungmin Cho, Soohyung Kim, Taesung Kim, Hyunchang Shin, Songhee Jung, Jiwoong Oh
  • Patent number: 10552966
    Abstract: An electronic device for quantifying parallax motion is described. The electronic device includes a detecting unit to detect at least three fiducial markers in an image with parallax, wherein the at least three fiducial markers are part of a straight line in an input image; an estimating unit to estimate a best fit line to a curved line formed by the at least three fiducial markers, wherein the curved line is a result of parallax applied to the input image; a calculating unit to calculate an error between the best fit line and the curved line formed by the at least three fiducial markers; and a comparing unit to compare the error to a threshold limit.
    Type: Grant
    Filed: March 7, 2016
    Date of Patent: February 4, 2020
    Assignee: Intel Corporation
    Inventors: Avigdor Eldar, Dror Cohen, Sagi Levi
  • Patent number: 10552658
    Abstract: A mobile device may include a first fingerprint sensor, including a platen, residing on a first side of the mobile device, and a display residing on a second side of the mobile device. The second side may be opposite from the first side. The mobile device may include a control system configured for communication with the first fingerprint sensor and the display. The control system may be further configured for receiving first fingerprint sensor signals from the first fingerprint sensor corresponding to a fingerprint contact area of a first finger positioned on the platen, for detecting one or more finger distortions corresponding to changes of the first fingerprint sensor signals and for controlling the mobile device based, at least in part, on the one or more finger distortions.
    Type: Grant
    Filed: March 24, 2017
    Date of Patent: February 4, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Jessica Liu Strohmann, Yair Karmi, Yipeng Lu, Hrishikesh Vijaykumar Panchawagh, David William Burns
  • Patent number: 10552953
    Abstract: A magnetic resonance imaging apparatus includes processing circuitry. The processing circuitry performs first imaging to acquire multiple magnetic resonance signals that are used to derive a quantitative value of tissue. The processing circuitry derives a quantitative value of tissue on the basis of the multiple magnetic resonance signals. The processing circuitry displays, on a display, an estimated image obtained by estimating, through a calculation, an image to be obtained by performing second imaging different from the first imaging on the basis of the derived quantitative value of tissue. The processing circuitry acquires an image by performing the second imaging in which an imaging parameter corresponding to the estimated image is set.
    Type: Grant
    Filed: December 12, 2016
    Date of Patent: February 4, 2020
    Assignee: Canon Medical Systems Corporation
    Inventor: Satoshi Sugiura
  • Patent number: 10552947
    Abstract: An image such as a light-field image may be processed to provide depth-based blurring. The image may be received in a data store. At an input device, first and second user input may be received to designate a first focus depth and a second focus depth different from the first focus depth, respectively. A processor may identify one or more foreground portions of the image that have one or more foreground portion depths, each of which is less than the first focus depth. The processor may also identify one or more background portions of the image that have one or more background portion depths, each of which is greater than the second focus depth. The processor may also apply blurring to the one or more foreground portions and the one or more background portions to generate a processed image, which may be displayed on a display device.
    Type: Grant
    Filed: November 28, 2017
    Date of Patent: February 4, 2020
    Assignee: GOOGLE LLC
    Inventors: Chia-Kai Liang, Kent Oberheu, Kurt Akeley, Garrett Girod, Nikhil Karnad, Francis A. Benevides
  • Patent number: 10545311
    Abstract: One embodiment of the present invention provides an image processing method, the method comprising: acquiring a plurality of viewpoint images; generating a contrast distribution from the plurality of viewpoint images; and generating an output image by performing image processing in accordance with the contrast distribution with respect to an image based on the plurality of viewpoint images.
    Type: Grant
    Filed: March 10, 2016
    Date of Patent: January 28, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventor: Koichi Fukuda
  • Patent number: 10540562
    Abstract: The present disclosure relates to a computer-implemented system and method for finding matching occurrences of an item of interest (or image or sub-image) within a document (or larger image) via cross correlation and setting a dynamic threshold for each document (or larger image). The described system and method are capable of matching and locating the one or more items of interest within each specific document (or larger image).
    Type: Grant
    Filed: December 12, 2017
    Date of Patent: January 21, 2020
    Assignee: Revenue Management Solutions, LLC
    Inventor: Jay Wagner