Patents Examined by Hadi Akhavannik
  • Patent number: 10318889
    Abstract: A method for training a deep neural network (DNN) to perform a specified task with respect to images captured by a target camera, including: using an image captured by the target camera as a style target image, training a style transformer network to perform a style transformation that transforms any photorealistic input image into a transformed image that has contents of the input image, maintains photorealistic quality of the input image, and has a style that matches a style of the style target image; using the trained style transformer network to transform training image of an original training dataset into transformed training images; labeling the transformed training images with the training labels of the corresponding training image of the original training dataset, to form an augmented training dataset; and using the augmented training dataset to train the DNN to perform the specified task.
    Type: Grant
    Filed: June 26, 2017
    Date of Patent: June 11, 2019
    Assignee: KONICA MINOLTA LABORATORY U.S.A., INC.
    Inventor: Ting Xu
  • Patent number: 10303931
    Abstract: An apparatus is for irradiating light for obtaining a face image of an authentication target. The apparatus includes a first light source unit having a first glancing angle, a second light source unit having a second glancing angle greater than the first glancing angle, and an external light information acquisition unit configured to acquire environment information on an external light other than the first light source unit and the second light source unit for the authentication target. The apparatus further includes a control unit configured to determine a power ratio of a second driving power supplied to the second light source unit to a first driving power supplied to the first light source unit based on the environment information and control currents to be supplied to the first light source unit and the second light source unit based on the power ratio.
    Type: Grant
    Filed: June 26, 2017
    Date of Patent: May 28, 2019
    Assignee: SUPREMA INC.
    Inventors: Hochul Shin, Kideok Lee, Dae Jin Kwon, Hyun Suk Lee, Bong Seop Song, Jae Won Lee
  • Patent number: 10303917
    Abstract: A biometric image processing apparatus includes an imaging device that captures a first image of a biometric part that is irradiated with light having a first wavelength, and a second image of the biometric part irradiated with light having a second wavelength shorter than the first wavelength, and a computing device that computes a third image by subtracting from the first image an image in which a luminance of the second image is attenuated.
    Type: Grant
    Filed: March 13, 2017
    Date of Patent: May 28, 2019
    Assignee: FUJITSU LIMITED
    Inventors: Soichi Hama, Satoshi Semba
  • Patent number: 10289889
    Abstract: In accordance with at least one embodiment, a touch sensor is disclosed. The touch sensor includes a first electroconductive pattern including at least two electrodes. The touch sensor further includes a second electroconductive pattern configured to mask a portion of the first electroconductive pattern when positioned over or under the first electroconductive pattern. The second electroconductive pattern masks the portion of the first electroconductive pattern such that an unmasked portion of the first electroconductive pattern includes unmasked portions of the at least two electrodes. The unmasked portions are of approximately equal length.
    Type: Grant
    Filed: May 19, 2017
    Date of Patent: May 14, 2019
    Assignee: SEMICONDUCTOR COMPONENTS INDUSTRIES, LLC
    Inventors: Takayasu Otagaki, Kazuyoshi Ishikawa
  • Patent number: 10289896
    Abstract: This invention relates to a method for face recognition and a device for implementing said method, the method comprising the steps of: displaying a point of interest on the screen such that a user adopts a gaze direction with respect to the screen; capturing an image of the user at the adopted gaze direction; and performing a face recognition algorithm on the image of the user, using an Enrollment image classified by said gaze direction.
    Type: Grant
    Filed: June 5, 2015
    Date of Patent: May 14, 2019
    Assignee: BRITISH TELECOMMUNICATIONS public limited company
    Inventors: Andrew Gordon Davis, Simon Giles Thompson
  • Patent number: 10282832
    Abstract: A method and installation of inspecting a fragmentation pattern of a tempered glass panel by deflectometry, following a fragmentation test, the method including: (i) positioning the tempered glass panel in contact with a support; (ii) projecting by a display device a structured light pattern on the surface of at least one portion of the tempered glass panel; (iii) capturing an image reflected by the surface of the first portion of the tempered glass panel using an image capture device; and (vi) processing the images to determine the fragmentation pattern by an image processing device.
    Type: Grant
    Filed: July 15, 2015
    Date of Patent: May 7, 2019
    Assignee: AGC GLASS EUROPE
    Inventors: Romain Dacquin, Nerio Lucca
  • Patent number: 10275892
    Abstract: A depth-based effect may be applied to a multi-view video stream to generate a modified multi-view video stream. User input may designate a boundary between a foreground region and a background region, at a different depth from the foreground region, of a reference image of the video stream. Based on the user input, a reference mask may be generated to indicate the foreground region and the background region. The reference mask may be used to generate one or more other masks that indicate the foreground and background regions for one or more different images, from different frames and/or different views from the reference image. The reference mask and other mask(s) may be used to apply the effect to the multi-view video stream to generate the modified multi-view video stream.
    Type: Grant
    Filed: March 17, 2017
    Date of Patent: April 30, 2019
    Assignee: GOOGLE LLC
    Inventors: Francois Bleibel, Tingfang Du, Thomas Nonn, Jie Tan
  • Patent number: 10275660
    Abstract: A method and apparatus for screening luggage are provided. X-ray images derived by scanning the luggage with X-rays are received and processed with an automated threat detection (ATD) engine. A determination is then made whether to subject respective ones of the X-ray images to further visual inspection by a human operator at least in part based on results obtained by the ATD engine. In certain cases, visual inspection by a human operator is by-passed and the ATD results are relied upon in order to mark luggage for further inspection or to mark luggage as clear. In another aspect, X-ray images derived by scanning the luggage using two or more X-ray scanning devices are pooled at a centralized location. ATD operations are applied to the X-ray images, which are then provided “on-demand” to a human operator for visual inspection. Results of the visual inspection are entered by the human operator and then conveyed to on-site screening technicians associated with respective X-ray scanning devices.
    Type: Grant
    Filed: August 8, 2017
    Date of Patent: April 30, 2019
    Assignee: VANDERLANDE APC INC.
    Inventor: Luc Perron
  • Patent number: 10275655
    Abstract: In accordance with one embodiment, an intelligent video thumbnail selection and generation tool may select a relevant and visually stimulating image from a video file and generate a thumbnail including the image. The image may be selected by computing a relevancy metric for an image in the file based on one or more selected relevant features, and comparing that relevancy metric with the metric of at least one other image in the file. In another embodiment, a series of images in a video file may be divided into shots. One of the shots may be selected based on a shot relevancy metric and a key image from the shot may be selected as a thumbnail based on a key image relevancy metric, where the shot relevancy metric and the key image relevancy metrics may be computed based on one or more relevant content features.
    Type: Grant
    Filed: November 27, 2017
    Date of Patent: April 30, 2019
    Assignee: BroadbandTV, Corp.
    Inventors: Shahrzad Rafati, Mehrdad Fatourechi, Lino Evgueni Coria Mendoza
  • Patent number: 10271095
    Abstract: A system and method for identifying media segments using audio augmented image cross-comparisoning is disclosed, in which a media segment identifying system analyzes both audio and video content, producing a unique identifier to compare with previously identified media segments in a media segment database. The characteristic landmark-linked-image-comparisones are constructed by first identifying pairs of audio landmarks separated by a characteristic, or landmark, time. Digital images associated the audio landmarks are then image comparisoned, with the combination providing a characteristic landmark-linked-image-comparison. The audio landmarks are audio peaks that exceed predetermined thresholds. A landmark-time is the time between adjacent pairs of audio peaks. The pair of images associated with the audio peaks are reduced in pixel size and converted to gray scale. Corresponding pixels are compared to form a numeric comparison.
    Type: Grant
    Filed: August 23, 2018
    Date of Patent: April 23, 2019
    Inventors: Samuel Chenillo, Oren Steinfeld
  • Patent number: 10262207
    Abstract: The present invention relates to a method for tracking a position of at least one keypoint in an image of an object moving relative to an optical sensor, wherein light reflected from the object (12) is detected so as to generate an image of the object, and wherein a position of at least one keypoint (Kj) in said image is detected and updated using temporal contrast events (Ev) of the optical sensor. The invention also relates to a corresponding computer program and device.
    Type: Grant
    Filed: July 24, 2015
    Date of Patent: April 16, 2019
    Assignee: UNIVERSITAT ZURICH
    Inventors: Tobias Delbruck, Christian Brandli, Marc Osswald
  • Patent number: 10255529
    Abstract: The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.
    Type: Grant
    Filed: March 13, 2017
    Date of Patent: April 9, 2019
    Assignee: Magic Leap, Inc.
    Inventors: Andrew Rabinovich, Vijay Badrinarayanan, Daniel DeTone, Srivignesh Rajendran, Douglas Bertram Lee, Tomasz Malisiewicz
  • Patent number: 10255488
    Abstract: Methods and systems for videoconferencing include recognition of emotions related to one videoconference participant such as a customer. This ultimately enables another videoconference participant, such as a service provider or supervisor, to handle angry, annoyed, or distressed customers. One example method includes the steps of receiving a video that includes a sequence of images, detecting at least one object of interest (e.g.
    Type: Grant
    Filed: December 1, 2017
    Date of Patent: April 9, 2019
    Assignee: Snap Inc.
    Inventors: Victor Shaburov, Yurii Monastyrshyn
  • Patent number: 10248837
    Abstract: Multi-resolution fingerprint sensors and methods of using the same are provided. The multi-resolution fingerprint sensors each include a portion of the imaging area or region of the sensor that provides higher imaging resolution than the remaining imaging area of the sensor. The area of higher resolution is useful for anti-spoofing purposes, but because only a portion of the sensor is higher-resolution, advantageously it will not impact hardware costs nearly as much as a sensor that was higher resolution over its entire imaging area. Furthermore, the higher resolution area can be down-sampled so there would be no impact on the standard matcher and image processing software stack, which expects a uniform resolution for the entire image acquired.
    Type: Grant
    Filed: February 13, 2018
    Date of Patent: April 2, 2019
    Assignee: Synaptics Incorporated
    Inventor: Anthony P. Russo
  • Patent number: 10244969
    Abstract: A fingerprint authentication method includes a first step of acquiring partial fingerprint measurement data for a part of a fingerprint, and a second step of calculating a matching rate by comparing the partial fingerprint measurement data with reference comparison data selected among a plurality of partial fingerprint registration data, each partial fingerprint registration data corresponding to a part of a fingerprint. The method further includes a third step of determining whether the matching rate is equal to or greater than an authentication threshold and a fourth step of determining, based on a result in the third step, a success of the authentication, or repeating the second and third steps by selecting new reference comparison data based on whether or not the matching rate is equal to or greater than a preset threshold smaller than the authentication threshold.
    Type: Grant
    Filed: June 26, 2017
    Date of Patent: April 2, 2019
    Assignee: SUPREMA INC.
    Inventors: Kideok Lee, Hochul Shin, Hyeonchang Lee, Jong Man Lee, Bong Seop Song, Jae Won Lee
  • Patent number: 10242465
    Abstract: A raw data set is acquired using a scan protocol via an imaging medical device. In an embodiment of a method, the raw data set and the scan protocol are transmitted from the medical device to a reconstruction unit. Furthermore, an at least two-dimensional image data set is calculated from the raw data set via the reconstruction unit. Furthermore, a display parameter is fetched via the reconstruction unit, the display parameter being assigned to the scan protocol and the display parameter defining a first projection method for the image data set. Furthermore, the image data set and the display parameter are transmitted from the reconstruction unit to a display unit, the reconstruction unit and the display unit being spatially separate. Furthermore, a first projection data set is determined by applying the first projection method to the image data set via the display unit.
    Type: Grant
    Filed: February 21, 2018
    Date of Patent: March 26, 2019
    Assignee: SIEMENS HEALTHCARE GMBH
    Inventor: Miriam Keil
  • Patent number: 10244167
    Abstract: Methods and apparatus for encoding and decoding image data based on one or more parameters. In one embodiment, various spatial portions or regions of image data (e.g., a still or moving image) are weighted according to the perceived or measured quality. Processing for these weighted regions can be selectively altered or adjusted so as to optimize one or more operational parameters including for example processing and/or memory requirements, or speed.
    Type: Grant
    Filed: February 14, 2017
    Date of Patent: March 26, 2019
    Assignee: GOPRO, INC.
    Inventors: Balineedu Chowdary Adsumilli, Adeel Abbas, Sumit Chawla
  • Patent number: 10242453
    Abstract: A pair of video frames may be used for simultaneous localization and mapping (SLAM) initialization. The pair of frames may be determined according to a translation threshold. Whether the translation threshold is met may be determined by obtaining the pair of video frames and estimating the translation between the frames.
    Type: Grant
    Filed: April 30, 2014
    Date of Patent: March 26, 2019
    Assignee: LONGSAND LIMITED
    Inventors: Pashmina Cameron, George Saklatvala
  • Patent number: 10237568
    Abstract: An image processing apparatus includes a division unit configured to divide an input image into a plurality of subblocks subjected to quantization control a subblock quantization parameter calculation unit configured to calculate a quantization parameter of each of the subblocks, a basic block quantization parameter calculation unit configured to set a basic block including at least two subblocks and to calculate a quantization parameter of the basic block, a difference value calculation unit configured to calculate a difference value between the quantization parameter of the basic block and the quantization parameter of each subblock included in the basic block, and a difference value coding unit configured to code the difference value.
    Type: Grant
    Filed: May 18, 2018
    Date of Patent: March 19, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Mitsuru Maeda
  • Patent number: 10235552
    Abstract: Systems, methods and apparatus for configuring a fingerprint sensor to operate in a capacitive sensing mode and an ultrasonic sensing mode are disclosed. A fingerprint sensor may be configured to operate in a capacitive sensing mode by driving a sensing electrode using a controller. In some implementations, an object positioned on or near the sensing electrode may be detected using the fingerprint sensor in the capacitive sensing mode, and the controller can drive electrodes of the fingerprint sensor differently to configure the fingerprint sensor to operate in an ultrasonic sensing mode. In some implementations, an applications processor may be instructed to authenticate a fingerprint of the object from image data obtained when the fingerprint sensor is operating in the ultrasonic sensing mode. In some implementations, a display of a mobile device containing the fingerprint sensor may be unlocked, or the mobile device may be woken up when the fingerprint is authenticated.
    Type: Grant
    Filed: June 26, 2017
    Date of Patent: March 19, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Sandeep Louis D'Souza, Vadim Winebrand, Ashish Hinger, Paul Penchin Pan, Meir Agassy, Yizhaq Abudi, Micah Timothy Lawrence, Jong Soo Kim, Sherman Sebastian Antao, Bo-Ren Wang, Masoud Roham, Lennart Karl Mathe, Nathan Felix Altman, Suryaprakash Ganti, David William Burns