Patents Examined by Sheela C Chawan
  • Patent number: 10319082
    Abstract: Presented is a method for identifying and removing one or more thin lines from a binary source image. The steps include generating a hole-filled intermediate binary image, and performing a thin line detection and removal process on the hole-filled intermediate binary image. The thin line detection and removal is performed by creating an eroded intermediate image, creating an opened intermediate image by performing a morphology dilation process, inverting the opened intermediate image, generating a density adjusted binary source image, generating a difference pixel intermediate image, generating a thin line subtraction intermediate image, and subtracting the thin line subtraction intermediate image from the binary source image to create a binary output image.
    Type: Grant
    Filed: May 30, 2017
    Date of Patent: June 11, 2019
    Assignee: ESKO SOFTWARE BVBA
    Inventor: Neil Xu
  • Patent number: 10307792
    Abstract: The present disclosure discloses an ultrasonic transducer. The ultrasonic transducer includes an active layer. The active layer includes an array of piezoelectric pillars configured for emitting and receiving ultrasound and an attenuation portion surrounding sidewalls of the piezoelectric pillars and configured for attenuating a part of the ultrasound emitted from the sidewalls of the piezoelectric pillars. The present disclosure also relates to an ultrasonic fingerprint recognition sensor and an electronic device having the ultrasonic transducer.
    Type: Grant
    Filed: April 19, 2017
    Date of Patent: June 4, 2019
    Assignee: NANCHANG O-FILM BIO-IDENTIFICATION TECHNOLOGY CO., LTD
    Inventors: Anpeng Bai, Wensi Sun
  • Patent number: 10311563
    Abstract: Certain example embodiments relate to detecting and recognizing coatings on articles. A captured image and/or video of an article includes source light reflections associated with each major surface of that article. A color coordinate characterization for each source light reflection is calculated. Detection and recognition of any coatings formed on the major surfaces of the article is performable by comparing the calculated color coordinate characterizations and/or changes between calculated color coordinate characterizations to information stored in a data store including known color coordinate characterizations and/or known changes between color coordinate characterizations for different known coatings.
    Type: Grant
    Filed: June 20, 2017
    Date of Patent: June 4, 2019
    Assignee: Guardian Steklo Services, LLC
    Inventor: Maxim Koldyshev
  • Patent number: 10311560
    Abstract: A method for estimating a blur kernel size, the method including: (1) pre-processing a blurred image, to obtain an image, so that a size of the image satisfies an image input size of a multi-class convolutional neural network (CNN); (2) inputting the image into a multi-class CNN with completed training, to obtain a blur-kernel-size probability distribution vector; and (3) comparing each element in the blur-kernel-size probability distribution vector, so that an estimated blur kernel size of the blurred image is the blur kernel size corresponding to a largest element. The invention also provides a system for estimating a blur kernel size. The system includes an image pre-processing module, a training-set synthesizing module, a multi-class CNN module, and a blur kernel size estimation module.
    Type: Grant
    Filed: September 19, 2017
    Date of Patent: June 4, 2019
    Assignee: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Nong Sang, Lerenhan Li, Luxin Yan, Changxin Gao, Yuanjie Shao, Juncai Peng, Shiwei Zhang, Jin Wang
  • Patent number: 10303962
    Abstract: Methods, computer readable storage media, and systems are provided for generating machine-readable biometric data from a medical device, which may include: obtaining an image of the medical device including a display of the medical device; retrieving a reference image of a reference display corresponding to the medical device, the reference image defining a reference data field within the reference display; comparing the image to the reference image to identify a data field within the display corresponding to the reference data field within the reference display; identifying one or more alpha-numeric symbols within the data field; and converting the alpha-numeric symbols into the machine-readable biometric data. The machine-readable biometric data may be used to create a data record for a user of the medical device, and can be communicated to an Independent Diagnostic Testing Facility (IDTF) database or server.
    Type: Grant
    Filed: April 27, 2016
    Date of Patent: May 28, 2019
    Assignee: ZTech, Inc.
    Inventors: Alan Chmiel, Christopher Sheehan, Bradley Humphreys
  • Patent number: 10303712
    Abstract: An image retrieval apparatus capable of retrieving a desired image from images shot continuously in a short time. A display control unit displays the images on a display unit in order in a first or second transition direction according to a user's operation. A setting unit sets up a limit point in the first (second) transition direction when the direction in which the images are displayed in order is switched from the first (second) transition direction to the second (first) transition direction based on an image displayed at a time of switching. The display control unit stops displaying the images in order in the first (second) transition direction when a displayed image reaches an image corresponding to the limit point in the first (second) transition direction during the images are displayed in order in the first (second) transition direction.
    Type: Grant
    Filed: May 30, 2017
    Date of Patent: May 28, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Yosato Hitaka
  • Patent number: 10290107
    Abstract: Aspects of the present disclosure involve a transform domain regression convolutional neural network for image segmentation. Example embodiments include a system comprising a machine-readable storage medium storing instructions and computer-implemented methods for classifying one or more pixels in an image. The method may include analyzing the image to estimate one or more transform domain coefficients using a multi-layered function such as a convolutional neural network. The method may further include generating a segmented image by applying a change of basis transformation to the estimated one or more transform domain coefficients.
    Type: Grant
    Filed: June 19, 2017
    Date of Patent: May 14, 2019
    Assignee: Cadence Design Systems, Inc.
    Inventors: Raúl Alejandro Casas, Samer Lutfi Hijazi, Rishi Kumar, Piyush Kaul, Xuehong Mao, Christopher Rowen, Himanshu Charaya
  • Patent number: 10289887
    Abstract: A fingerprint sensor includes a detection area to be touched by a user with a finger. The fingerprint sensor has a detection mode including a first detection mode in which the fingerprint sensor does not detect a fingerprint of the finger that is in contact with the detection area and a second detection mode in which the fingerprint sensor detects the fingerprint. At least one processor is configured to set the detection mode to the second detection mode when a predetermined condition is failed to be met while a display mode is set to a first display mode in which a display displays no information. Also, the at least one processor is configured to set the detection mode to the first detection mode when the predetermined condition is met while the display mode is set to the first display mode.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: May 14, 2019
    Assignee: KYOCERA CORPORATION
    Inventor: Toshiyuki Kumano
  • Patent number: 10275629
    Abstract: The present invention relates to a method for extracting morphological characteristics from a sample of biological material, in particular fingerprints, especially internal or external fingerprints, using an optical coherence tomography acquiring system delivering a signal representative of the sample, in which method an image containing intensity data and an image containing phase data are formed from at least the signal delivered by the acquiring system and representative of the sample, in order to extract the morphological characteristics from the sample.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: April 30, 2019
    Assignee: IDEMIA IDENTITY & SECURITY
    Inventors: François Lamare, Yaneck Gottesman, Bernadette Dorizzi
  • Patent number: 10268862
    Abstract: A fingerprint collection method includes: acquiring, by a fingerprint collector, a fingerprint image of a user; if an average value of the fingerprint image is not in a preset average value range, automatically adjusting a gain of the fingerprint collector, to make an average value of a reacquired fingerprint image approximate the preset average value range; if the average value of the fingerprint image is in the preset average value range, but a variance of the fingerprint image is less than a preset variance threshold, automatically increasing sensitivity of the fingerprint collector, to make a variance of the fingerprint collector accordingly increase; and outputting only a fingerprint image whose average value is in the preset average value range and whose variance is greater than the preset variance threshold.
    Type: Grant
    Filed: April 16, 2015
    Date of Patent: April 23, 2019
    Assignee: Huawei Technologies Co., Ltd.
    Inventor: Danhong Li
  • Patent number: 10269099
    Abstract: An image-processing method of removing noise from an image includes: obtaining standard representative values for standard regions of a standard image and reference representative values for reference regions of a reference image, and obtaining a plurality of hierarchical images having different resolutions with respect to the standard image and the reference image based on the standard representative values and the reference representative values; obtaining the standard representative values for the standard regions of the standard image and the reference representative values for the reference regions of the reference image from the hierarchical images; determining a similarity between the standard regions and the reference regions from the standard representative values and the reference representative values; and removing noise by applying filtering to the standard image and the reference image depending on the determined similarity.
    Type: Grant
    Filed: October 13, 2015
    Date of Patent: April 23, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jong-hun Lee, Young-su Moon, Yong-min Tai
  • Patent number: 10262427
    Abstract: The present invention addresses the problem of providing a technique for determining the authenticity of a product without requiring a special device such as an integrated circuit (IC) tag. A means for solving this problem according to the invention is characterized by determining the authenticity of a target product on the basis of the validity of the association between the body of the product and a surface-treated component that is mounted to the body and that has been validated.
    Type: Grant
    Filed: August 31, 2015
    Date of Patent: April 16, 2019
    Assignee: NEC Corporation
    Inventors: Toru Takahashi, Rui Ishiyama
  • Patent number: 10255668
    Abstract: Embodiments can provide a computer implemented method in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to cause the processor to implement a system for providing profile photo enhancement, the method comprising receiving, from an online platform, one or more specifications for image acceptance criteria; receiving, through an uploading user, a plurality of images; receiving, through a requesting user, a request to view an image; selecting a particular specification for image acceptance criteria; for each image in the plurality of images: examining, through an image processing toolbox, the image to determine if the image acceptance criteria are met; if all acceptance criteria are met, providing the image to the requesting user; if one or more acceptance criteria are not met, taking one or more actions to process the image, reexamining, through the image processing toolbox, the processed image to determine if the image acceptan
    Type: Grant
    Filed: August 23, 2016
    Date of Patent: April 9, 2019
    Assignee: International Business Machines Corporation
    Inventors: Paul R. Bastide, John M. Boyer
  • Patent number: 10255477
    Abstract: In one aspect, methods that use a novel representation, referred to as an octant feature vector (OFV), are used for matching distorted fingerprints. For instance, a feature-based matcher for distorted fingerprint matching may use a two-step local and global matching scheme to compare a set of feature vectors that are derived from minutiae of a reference fingerprint and a search fingerprint. The relative geometric relationships between the reference minutia and nearest minutiae may be derived and encoded into a feature vector based on orientation difference. The OFV is invariant to the rigid transformations and is insensitive to nonlinear distortions since the relative geometric relationships are independent from the rigid transformation.
    Type: Grant
    Filed: May 31, 2017
    Date of Patent: April 9, 2019
    Assignee: MorphoTrak, LLC
    Inventors: Peter Zhen-Ping Lo, Hui Chen
  • Patent number: 10248861
    Abstract: A system for identifying an unmanned moving object, including: a mobile terminal, an unmanned moving object provided with moving means for enabling the object to move arbitrarily, a management server provided with a database to which specific information including possessor information of the unmanned moving object and individual object management information correlating with the specific information are input, and a communication network which enables communication between the mobile terminal and the management server, wherein identification information that is acquired when a user of the mobile terminal has encountered the unmanned moving object is associated with the individual object management information in advance and the mobile terminal acquires the identification information, acquires specific information by checking the identification information of the mobile terminal for a match within the individual object management information on the management server, and ascertains the possessor information o
    Type: Grant
    Filed: May 10, 2016
    Date of Patent: April 2, 2019
    Assignee: PRODRONE CO., LTD.
    Inventor: Kazuo Ichihara
  • Patent number: 10248891
    Abstract: Concepts and technologies disclosed herein are directed to image prediction. According to one aspect disclosed herein, an image prediction system can receive a training data set that includes a plurality of training images. The image prediction system can define N-dimensional feature vectors corresponding to the plurality of training images in the training data set, parameterize the N-dimensional feature vectors to obtain a plurality of parameterized curves corresponding the plurality of training images in the training data set, obtain a square root velocity representation for each parameterized curve of the plurality of parameterized curves, rescale the plurality of parameterized curves to remove scaling variability among the plurality of parameterized curves, define a pre-shape space for the plurality of parameterized curves, and obtain shape space points pertaining to each parameterized curve of the plurality of parameterized curves on a shape space that inherits a structure from the pre-shape space.
    Type: Grant
    Filed: June 20, 2017
    Date of Patent: April 2, 2019
    Assignee: AT&T Intellectual Property I, L.P.
    Inventor: Raghuraman Gopalan
  • Patent number: 10248881
    Abstract: In order to acquire recognition environment information impacting the recognition accuracy of a recognition engine, an information processing device 100 comprises a detection unit 101 and an environment acquisition unit 102. The detection unit 101 detects a marker, which has been disposed within a recognition target zone for the purpose of acquiring information, from an image captured by means of an imaging device which captures images of objects located within the recognition target zone. The environment acquisition unit 102 acquires the recognition environment information based on image information of the detected marker. The recognition environment information is information representing the way in which a recognition target object is reproduced in an image captured by the imaging device when said imaging device captures an image of the recognition target object located within the recognition target zone.
    Type: Grant
    Filed: August 19, 2015
    Date of Patent: April 2, 2019
    Assignee: NEC Corporation
    Inventor: Hiroo Ikeda
  • Patent number: 10235772
    Abstract: An installation error detection apparatus of an onboard camera includes: an input portion that receives a photographed image; a storage portion that stores position information of a feature point of the vehicle; a feature point detection portion; a determination portion that determines whether the installation position of the onboard camera is the proper position; and a notification portion that informs installation defect of the onboard camera. The notification portion calculates the installation position of the onboard camera required to minimize the deviation amount and corrects the photographed image by the onboard camera. The notification portion detects the feature point and calculates a similarity degree of the position of the feature point and the position information. The notification portion determines the installation defect of the onboard camera and informs the installation defect. The notification portion determines that a vehicle body is deformed and informs the vehicle body being deformed.
    Type: Grant
    Filed: March 24, 2015
    Date of Patent: March 19, 2019
    Assignee: DENSO CORPORATION
    Inventors: Bingchen Wang, Masakazu Takeichi, Muneaki Matsumoto
  • Patent number: 10210598
    Abstract: An electronic device and a method for processing an image are provided. The electronic device includes a display configured to display a plurality of images on a screen and a processor configured to detect a number of objects included in each of the plurality of images, determine a scaling factor for each of the plurality of images based on the detected number of objects, resize one or more images among the plurality of images based on the determined scaling factor for each of the plurality of images, and control at least one of a layout and a display order of the plurality of images based on the resized images and control the display to display the plurality of images.
    Type: Grant
    Filed: June 3, 2016
    Date of Patent: February 19, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Anish Anil Patankar, Joy Bose
  • Patent number: 10204408
    Abstract: Apparatus, system and method for detecting defects in an adhesion area that includes an adhesive mixed with a fluorescent material. One or more illumination devices may illuminate the fluorescent material in the adhesion area with a light of a predetermined wavelength. A camera may be configured to capture an image of the illuminated adhesion area. A processing device, communicatively coupled to the camera, may be configured to process the captured image by applying one or more boundary areas to the captured image and determining an image characteristic within each of the boundary areas, wherein the image characteristic is used by the processing device to determine the presence of a defect in the adhesive, such as an excess of adhesive or an insufficient application of adhesive.
    Type: Grant
    Filed: January 23, 2017
    Date of Patent: February 12, 2019
    Assignee: Jabil Inc.
    Inventors: Quyen Duc Chu, Nazir Ahmad