Patents Examined by Yosef Kassa
  • Patent number: 10475207
    Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.
    Type: Grant
    Filed: August 7, 2018
    Date of Patent: November 12, 2019
    Assignee: Adobe Inc.
    Inventors: Jimei Yang, Yu-Wei Chao, Scott Cohen, Brian Price
  • Patent number: 10475176
    Abstract: Provided is an inspection system for a wire electrical discharge machine, capable of automatically performing inspection of a constituent element and the like. The inspection system for a wire electrical discharge machine is provided with the wire electrical discharge machine, a robot for inspecting the constituent element of the wire electrical discharge machine, an image pickup device provided on a movable part of the robot and configured to image the constituent element, an image processing unit configured to acquire an image of the constituent element by means of the image pickup device, and a maintenance necessity determination unit configured to determine the necessity of maintenance of the constituent element based on the image acquired by the image processing unit.
    Type: Grant
    Filed: February 27, 2017
    Date of Patent: November 12, 2019
    Assignee: FANUC CORPORATION
    Inventor: Kazutaka Nakayama
  • Patent number: 10474872
    Abstract: A fingerprint matching system for fingerprint matching using virtual minutiae includes a fingerprint scanning device, including (i) an interface to a fingerprint scanner, and (ii) a sensor associated with the fingerprint scanner, configured to identify a match between a search fingerprint representing a fingerprint of a subject and a reference fingerprint from among a plurality of reference fingerprints representing fingerprints of a plurality of historical subjects; a database containing the plurality of reference fingerprints representing fingerprints of the plurality of historical subjects; and a computing device in communication with said database and said fingerprint scanning device.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: November 12, 2019
    Assignee: MorphoTrak, LLC
    Inventors: Hui Zhu, Peter Zhen-Ping Lo, Hui Chen
  • Patent number: 10475164
    Abstract: One or more processors may perform one or more lookup table (LUT)-based image processing operations on an input image to produce an output image, wherein performing the one or more image processing operations on the input image introduces one or more banding artifacts in the output image. The one or more processors may determine one or more sub-regions of the output image that include the one or more banding artifacts. The one or more processors may perform one or more artifact reduction operations on the one or more sub-regions of the output image without performing the one or more artifact reduction operations on remaining sub-regions of the output image.
    Type: Grant
    Filed: September 12, 2017
    Date of Patent: November 12, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Shreyas Hampali Shivakumar, Ajit Venkat Rao, Yogesh Gupta, Conrad A. Harrison
  • Patent number: 10463334
    Abstract: A system and method are provided for generating time resolved series of angiographic volume data having flow information. The system and method are configured to receive angiographic volume data acquired from a subject having received a dose of a contrast agent using an imaging system and process the angiographic volume data to generate angiographic volume images. The angiographic volume data is processed to select a seed vessel in the vessel network, determine a plurality of branch vessels connected to the seed vessel and extending to form a vessel network, determine independent and dependent vessels in the vessel network, apply a flow model to the vessel network, and generate a flow map to be displayed with the angiographic volume images to illustrate time-resolved vascular volumes displaying flow within the vessel network.
    Type: Grant
    Filed: January 16, 2018
    Date of Patent: November 5, 2019
    Assignee: Wisconsin Alumni Research Foundation
    Inventor: Gabriel Grant Shaughnessy
  • Patent number: 10460145
    Abstract: A device for capturing imprints of a body part on-the-fly, including a stand which includes a region of free space through which a user may pass a body part. When in this zone, the body part is simultaneously illuminated by a light source that produces a uniform illumination of the body part and a sight-projecting module that projects a sight onto the body part, and an image of the body part thus illuminated is acquired by the image-acquiring module. The capturing device is able to model the variations in light intensity of the projection of the sight on the body part by determining parameters of a preset parametric mathematical model, and generate a synthetic image of said projection on the basis of said model and using parameters determined beforehand. The synthetic image is then subtracted from the acquired image in order to obtain a sight-free image of the body part.
    Type: Grant
    Filed: May 7, 2018
    Date of Patent: October 29, 2019
    Assignee: IDEMIA IDENTITY & SECURITY FRANCE
    Inventor: Laurent Trouboul
  • Patent number: 10460427
    Abstract: Embodiments relate to converting imagery to a polar projection. Initially, a map request that specifies the polar projection for a geographic area is obtained. The geographic area into a number of image regions. A first source image is obtained for a first image region, where the first source image is at a first target resolution, and a second source image is obtained for a second image region, where the second source image is at a second target resolution that is determined based on a geographic location of the second image region. The first source image and the second source image are projected into the polar projection to obtain a single output image. At this stage, a polar coordinate system that corresponds to the polar projection is used to render the single output image in a spatial map.
    Type: Grant
    Filed: November 22, 2017
    Date of Patent: October 29, 2019
    Assignee: The Government of the United States of America, as represented by the Secretary of the Navy
    Inventors: John T. Sample, Elias Z. K. Ioup, Bruce Y. Lin
  • Patent number: 10452891
    Abstract: A method of identifying similar media items is described. The method include identifying a first multiplicity of fingerprints representative of content segments of variable duration for a first media item and a second multiplicity of fingerprints representative of content segments of variable duration for a second media item. The method further includes comparing, by a processing device, a first group of the first multiplicity of fingerprints to a second group of the second multiplicity of fingerprints to generate a first similarity score indicative of a similarity between the first group of fingerprints and the second group of fingerprints. The method also includes determining an alignment score for the first multiplicity of fingerprints and the second multiplicity of fingerprints using the first similarity score.
    Type: Grant
    Filed: April 30, 2018
    Date of Patent: October 22, 2019
    Assignee: Google LLC
    Inventors: Pedro Gonnet Anders, Filip Pavetic
  • Patent number: 10452071
    Abstract: A method for identifying objects by an autonomous robot. Images of a work environment are captured by an image sensor positioned on the autonomous robot. An object dictionary containing image data regarding a set of objects is preloaded into the system. Captured images are transmitted to an image processor that processes the images to generate feature vector and identify objects within the images by comparison to objects in the object dictionary. Upon identifying an object in an image as an object from the object dictionary, the system executes a set of preprogrammed responses, which may include altering a movement path to avoid colliding with or driving over the object.
    Type: Grant
    Filed: February 27, 2017
    Date of Patent: October 22, 2019
    Assignee: AI Incorporated
    Inventors: Ali Ebrahimi Afrouzi, Soroush Mehrnia
  • Patent number: 10440307
    Abstract: A control unit 21 of a main device 20 is configured to recognize a predetermined subject (face of person) included in a wide-angle image taken by an imaging device 10 and to correct distortion of an image (face image of the person) of a part of the subject, and to associate a part of the wide-angle image with the corrected image of the part of the subject, e.g., to display a part of the wide-angle image with the corrected image of the part of the subject on a reproduction screen.
    Type: Grant
    Filed: September 30, 2016
    Date of Patent: October 8, 2019
    Assignee: CASIO COMPUTER CO., LTD.
    Inventor: Yoshihiro Takayama
  • Patent number: 10438322
    Abstract: Resolution enhancement techniques are described. An apparatus may receive first image data at a first resolution, and second image data at a resolution less than the first resolution. The second image data may be scaled to the first resolution and compared to the first image data. Application of a neural network may scale the first image data to a resolution higher than the first resolution. The application of the neural network may incorporate signals based on the scaled second image data. The signals may include information obtained by comparing the scaled second image data to the resolution of the first image data.
    Type: Grant
    Filed: May 26, 2017
    Date of Patent: October 8, 2019
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Moshe R. Lutz, Vivek Pradeep
  • Patent number: 10438329
    Abstract: The method provided in the present disclosure includes: obtaining an image photographed by a camera, and performing face detection on the image by using a face detection algorithm, to obtain a face pixel set from the image; positioning a facial feature contour mask over the face pixel set, to obtain a to-be-examined pixel set from the face pixel set, the to-be-examined pixel set including: a plurality of pixels within an image area except pixels masked by the facial feature contour mask in the face pixel set; performing edge contour detection on the to-be-examined pixel set, and extracting one or more blemish regions from the to-be-examined pixel set, to obtain a to-be-retouched pixel set, the to-be-retouched pixel set including: a plurality of pixels within an image area belonging to the blemish regions; and retouching all pixels in the to-be-retouched pixel set, to obtain a retouched pixel set.
    Type: Grant
    Filed: September 8, 2017
    Date of Patent: October 8, 2019
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Guofu Tan, Jilin Li
  • Patent number: 10430689
    Abstract: This disclosure relates to training a classifier algorithm that can be used for automatically selecting tags to be applied to a received image. For example, a computing device can group training images together based on the training images having similar tags. The computing device trains a classifier algorithm to identify the training images as semantically similar to one another based on the training images being grouped together. The trained classifier algorithm is used to determine that an input image is semantically similar to an example tagged image. A tag is generated for the input image using tag content from the example tagged image based on determining that the input image is semantically similar to the tagged image.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: October 1, 2019
    Assignee: Adobe Inc.
    Inventors: Zhe Lin, Stefan Guggisberg, Jonathan Brandt, Michael Marth
  • Patent number: 10430680
    Abstract: A method is claimed for allocating processor/computing times of a processor or of a computing unit for a vehicle system of a vehicle. The vehicle system is in particular a driver assistance system. The vehicle system has at least two functions, in particular two functions of the driver assistance system, to which processor/computing times are allocated as a function of a signal that represents a state of the vehicle.
    Type: Grant
    Filed: September 13, 2017
    Date of Patent: October 1, 2019
    Assignee: Robert Bosch GmbH
    Inventors: Florian Weimer, Matthias Birk, Omar Alaa El-Din, Steffen Brueggert, Tobias Rentschler
  • Patent number: 10430632
    Abstract: An exemplary embodiment of the present inventive concept provides a display device including: a display unit including a plurality of pixels disposed on a display area; a display controller configured to control the display unit; a sensor including a plurality of first sensing electrodes and a plurality of second sensing electrodes disposed in the display area; and a sensor controller configured to recognize a touch of a user inputted into the sensor in a touch sensing mode and to recognize a fingerprint of the user inputted into the sensor in a fingerprint sensing mode, wherein the sensor controller changes a mode to the fingerprint sensing mode when no touch is inputted for a predetermined time period in the touch sensing mode and changes the mode to the touch sensing mode when authorization on a fingerprint inputted into the sensor is succeeded in the fingerprint sensing mode.
    Type: Grant
    Filed: January 9, 2017
    Date of Patent: October 1, 2019
    Assignee: Samsung Display Co., Ltd.
    Inventors: Won Ki Hong, Jong Seo Lee
  • Patent number: 10424055
    Abstract: The invention realizes, with a circuit size having a small number of multipliers, one-dimensional cubic interpolation, which is a primitive calculation of two-dimensional bicubic interpolation that is often used as high image quality interpolation processing of images. An image processing apparatus includes a first linear interpolation calculator that generates an interpolated pixel value at an interpolation position through linear interpolation, based on pixel values of a pair of pixels among a plurality of pixels, a plurality of second linear interpolation calculators that generate a plurality of correction values by respectively performing linear interpolation based on a pair of difference values among a plurality of difference values between pixel values of the plurality of pixels, and a calculator that generates a pixel value at the interpolation position based on the interpolated pixel value and the plurality of correction values.
    Type: Grant
    Filed: May 25, 2017
    Date of Patent: September 24, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Tadayoshi Nakayama
  • Patent number: 10419753
    Abstract: A display area can be smoothly moved. A semiconductor device sequentially receives a plurality of whole images, each of which includes a plurality of small screen images and which are temporally continuous and form a moving image, and decodes a received whole image. Here, the semiconductor device includes a reception unit that receives the whole image including the small screen images, a determination unit that determines a decoding area which includes a small screen image to be decoded and which is included in the whole image, and a decoding unit that decodes the small screen image in the decoding area which is determined by the determination unit and which is included in the whole image. The determination unit determines a new decoding area when a small screen image of intra frame appears in the decoding area.
    Type: Grant
    Filed: September 8, 2017
    Date of Patent: September 17, 2019
    Assignee: RENESAS ELECTRONICS CORPORATION
    Inventors: Kazushi Akie, Seiji Mochizuki, Toshiyuki Kaya, Katsushige Matsubara, Hiroshi Ueda, Ren Imaoka, Ryoji Hashimoto
  • Patent number: 10402702
    Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.
    Type: Grant
    Filed: April 19, 2018
    Date of Patent: September 3, 2019
    Assignee: International Business Machines Corporation
    Inventors: Somnath Asati, Soma Shekar Naganna, Abhishek Seth, Vishal Tomar, Shashidhar R. Yellareddy
  • Patent number: 10395146
    Abstract: A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.
    Type: Grant
    Filed: April 19, 2018
    Date of Patent: August 27, 2019
    Assignee: International Business Machines Corporation
    Inventors: Somnath Asati, Soma Shekar Naganna, Abhishek Seth, Vishal Tomar, Shashidhar R. Yellareddy
  • Patent number: 10395090
    Abstract: In some implementations, a computer-implemented method includes: obtaining a captured image including, (i) a latent fingerprint to be captured, and (ii) a template, surrounding the latent fingerprint, that contains plurality of symbols; extracting, using an image processing technique, one or more characteristics for each of the plurality of symbols; calculating a resolution for the captured image based at least on the extracted one or more characteristics for each of the plurality of symbols; generating a reconstructed desired image, based at least on (i) the calculated resolution of the captured image, and (ii) the one or more extracted characteristics for each of the plurality of symbols; and providing the reconstructed desired image to a fingerprint identification system to perform a particular fingerprint operation.
    Type: Grant
    Filed: April 2, 2018
    Date of Patent: August 27, 2019
    Assignee: MorphoTrak, LLC
    Inventors: Laurent Semy Kazdaghli, Peter Zhen-Ping Lo, Jean-Christophe Francois Marie Fondeur