Patents Examined by Jayesh A Patel
  • Patent number: 10311589
    Abstract: One embodiment of the present invention sets forth a technique for estimating a head pose of a user. The technique includes acquiring depth data associated with a head of the user and initializing each particle included in a set of particles with a different candidate head pose. The technique further includes performing one or more optimization passes that include performing at least one iterative closest point (ICP) iteration for each particle and performing at least one particle swarm optimization (PSO) iteration. Each ICP iteration includes rendering the three-dimensional reference model based on the candidate head pose associated with the particle and comparing the three-dimensional reference model to the depth data. Each PSO iteration comprises updating a global best head pose associated with the set of particles and modifying at least one candidate head pose. The technique further includes modifying a shape of the three-dimensional reference model based on depth data.
    Type: Grant
    Filed: November 27, 2017
    Date of Patent: June 4, 2019
    Assignee: NVIDIA CORPORATION
    Inventors: Gregory P. Meyer, Shalini Gupta, Iuri Frosio, Nagilla Dikpal Reddy, Jan Kautz
  • Patent number: 10311752
    Abstract: A method of generating a map for image aided navigation comprises detecting one or more edges in one or more terrain images, and obtaining a compressed edge representation of the one or more edges. The compressed edge representation is obtained by a method comprising fitting a geometric form or other mathematical model to the one or more edges, calculating one or more coefficients based on the fitted geometric form or other mathematical model, and storing the one or more coefficients in a database for use in generating the map for image aided navigation.
    Type: Grant
    Filed: February 3, 2017
    Date of Patent: June 4, 2019
    Assignee: Honeywell International Inc.
    Inventors: Michael Ray Elgersma, Benjamin Mohr
  • Patent number: 10311098
    Abstract: A system and method for storing data may include: unevenly dividing the image into polygonal image sections having pixels with band(s) and a bit depth per band that is too high for displaying on a display screen, dividing the image into quads such that each quad has a boundary that contains a portion of one of the polygonal image sections, obtaining statistical data computed for each of the bands of each of the pixels within each of the polygonal image sections, storing, with respect to a reduced resolution dataset (R-Set) of the image, coordinates of bounds of a polygonal image section that intersects with a quad, organizing the image, the quads, and the polygonal image sections in a tree structure, and storing the statistical data, the pixel coordinates, and the tree structure.
    Type: Grant
    Filed: July 11, 2018
    Date of Patent: June 4, 2019
    Assignee: PIXIA CORP.
    Inventor: Rahul C. Thakkar
  • Patent number: 10313574
    Abstract: A device for recognizing the inscription on the wall of a tire, including a driving surface plane, at least one directional light source to illuminate the tire; at least one camera to record multiple images of a wall of the tire rolling on the driving surface plane; and an evaluation device to synthesize an image of the wall of the tire from the multiple recorded images and to evaluate the synthesized image with the aid of a text recognition method.
    Type: Grant
    Filed: February 27, 2014
    Date of Patent: June 4, 2019
    Assignee: Beissbarth GmbH
    Inventors: Christian Hanel, Volker Uffenkamp, Michael Klar, Guenter Nobis
  • Patent number: 10296811
    Abstract: A user's collection of images may be analyzed to identify people's faces within the images, then create clusters of similar faces, where each of the clusters may represent a person. The clusters may be ranked in order of size to determine a relative importance of the associated person to the user. The ranking may be used in many social networking applications to filter and present content that may be of interest to the user. In one use scenario, the clusters may be used to identify images from a second user's image collection, where the identified images may be pertinent or interesting to the first user. The ranking may also be a function of user interactions with the images, as well as other input not related to the images. The ranking may be incrementally updated when new images are added to the user's collection.
    Type: Grant
    Filed: August 30, 2016
    Date of Patent: May 21, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Eyal Krupka, Igor Abramovski, Igor Kviatkovsky
  • Patent number: 10284922
    Abstract: The present invention relates to an advertisement detection system based on fingerprints, and provides an advertisement detection systems based on fingerprints, including a content stream storage unit for storing broadcast content in real time, a section selection unit for selecting a reference section and a test section from broadcast content stored by the content stream storage unit, a fingerprint extraction unit for extracting fingerprints from the reference section and the test section selected by the section selection unit using one or more methods, a fingerprint matching unit for comparing the fingerprints from the test section and the reference section, extracted by the fingerprint extraction unit, with each other and then performing matching between the fingerprints, an advertisement section determination unit for determining advertisement segments from the test section based on results of the matching performed by the fingerprint matching.
    Type: Grant
    Filed: September 17, 2018
    Date of Patent: May 7, 2019
    Assignee: Enswers Co., Ltd.
    Inventors: Hoon-Young Cho, Jaehyung Lee
  • Patent number: 10268920
    Abstract: A method for image processing is provided. The method includes: generating a skeleton graph associated with the table and comprising a plurality of edges; identifying, in the skeleton graph, a corner vertex, a starting vertex adjacent to the corner vertex, and an ending vertex adjacent to the corner vertex; determining a set of route options for the starting vertex that includes a first set of vertices adjacent to the starting vertex; selecting a candidate vertex from the first set of vertices as a first vertex; determining a set of route options for a second vertex comprising a second set of vertices adjacent to the second vertex; determining the second set of vertices comprises the ending vertex; and generating a route for a cell in the table and comprising the corner vertex, the starting vertex, the first vertex, the second vertex, and the ending vertex.
    Type: Grant
    Filed: August 31, 2017
    Date of Patent: April 23, 2019
    Assignee: Konica Minolta Laboratory U.S.A., Inc.
    Inventor: Darrell Eugene Bellert
  • Patent number: 10262187
    Abstract: Disclosed are systems and methods for performing spoof detection. The method includes: receiving, by a processor from a biometric sensor, an input image of a biometric; analyzing the input image to identify pixels associated with a first feature in the input image; performing a local binary pattern (LBP) analysis on the pixels associated with the first feature, which comprises computing, for a given pixel associated with the first feature, an LBP value corresponding to texture of one or more neighboring pixels around the given pixel, wherein the neighboring pixels around the given pixel comprise eight pixels around the given pixel, including pixels on a top, a bottom, a left, a right, and at four corners of a location of the given pixel; and, determining whether the input image is a replica of the biometric based on results of performing the LBP analysis on the pixels associated with the first feature.
    Type: Grant
    Filed: December 22, 2016
    Date of Patent: April 16, 2019
    Assignee: Synaptics Incorporated
    Inventor: Anthony P. Russo
  • Patent number: 10223770
    Abstract: An image processing apparatus includes a setting unit configured to set a virtual light source for a captured image; a brightness correction unit configured to correct brightness of a partial region of an object using the virtual light source set by the setting unit; an attribute detection unit configured to detect an attribute of the partial region; a glossy component generation unit configured to generate a glossy component that is to be applied to the partial region, according to the attribute of the partial region detected by the attribute detection unit; and a glossy appearance correction unit configured to correct a glossy appearance of the partial region using the glossy component generated by the glossy component generation unit.
    Type: Grant
    Filed: May 4, 2016
    Date of Patent: March 5, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Kaori Tajima
  • Patent number: 10210422
    Abstract: In order to shorten a time required to detect structure information of an image, in an image obtained by photographing a subject, feature amounts of pixel values in a block including a plurality of pixels are calculated, and the structure information is detected every (N×N) area of an input image on the basis of a combination of the feature amounts of the pixel values in a plurality of blocks.
    Type: Grant
    Filed: December 22, 2016
    Date of Patent: February 19, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Tetsuhiko Yao
  • Patent number: 10198689
    Abstract: Described is a system for object detection in images or videos using spiking neural networks. An intensity saliency map is generated from an intensity of an input image having color components using a spiking neural network. Additionally, a color saliency map is generated from a plurality of colors in the input image using a spiking neural network. An object detection model is generated by combining the intensity saliency map and multiple color saliency maps. The object detection model is used to detect multiple objects of interest in the input image.
    Type: Grant
    Filed: September 19, 2016
    Date of Patent: February 5, 2019
    Assignee: HRL Laboratories, LLC
    Inventors: Yongqiang Cao, Qin Jiang, Yang Chen, Deepak Khosla
  • Patent number: 10198830
    Abstract: An information processing apparatus includes a correlation unit that correlates distance information indicating a distance to an emission position of electromagnetic waves emitted in a shooting direction of a plurality of image pickup units with a first pixel in a first image that constitutes images taken by the image pickup units, the distance information being obtained based on reflected waves of the electromagnetic waves and the first pixel corresponding to the emission position of the electromagnetic waves, and a generation unit that generates a parallax image by using the distance information correlated with the first pixel for parallax computation of pixels in a second image that constitutes the images.
    Type: Grant
    Filed: December 22, 2014
    Date of Patent: February 5, 2019
    Assignee: Ricoh Company, Ltd.
    Inventors: Hiroyoshi Sekiguchi, Soichiro Yokota, Shuichi Suzuki, Shin Aoki, Haike Guan, Jun Yoshida, Mitsuru Nakajima, Hideomi Fujimoto
  • Patent number: 10192288
    Abstract: The present invention presents four fusion approaches, which can be directly applied to Worldview-3 (WV-3) images. Moreover, they can also be applied to other current or future satellite images that have similar characteristics of WV-3. The present invention also presents data processing methods, including image fusion method, anomaly detection method, material classification method, and concentration estimation method that utilize the high-resolution images generated by the mentioned fusion methods. There are four fusion approaches disclosed in the present invention, e.g. Parallel one-step fusion approach; Sequential fusion of various bands; Sequential-Parallel fusion; and Parallel-Sequential fusion.
    Type: Grant
    Filed: December 23, 2016
    Date of Patent: January 29, 2019
    Assignee: Signal Processing, Inc.
    Inventor: Chiman Kwan
  • Patent number: 10176406
    Abstract: A machine may be configured to perform image evaluation of images depicting items for online publishing. For example, the machine performing a user behavior analysis based on data pertaining to interactions by a plurality of users with a plurality of images pertaining to a particular type of item. The machine determines, based on the user behavior analysis, that a presentation type associated with one or more images of the plurality of images corresponds to a user behavior in relation to the one or more images. The machine determines that an item included in a received image is of the particular type of item. The machine generates an output for display in a client device. The output includes a reference to the received image and a recommendation of the presentation type for the item included in the received image, for publication by a web server of a publication system.
    Type: Grant
    Filed: May 10, 2016
    Date of Patent: January 8, 2019
    Assignee: eBay Inc.
    Inventors: Wei Di, Vignesh Jagadeesh, Robinson Piramuthu, Elizabeth Churchill, Anurag Bhardwaj
  • Patent number: 10169643
    Abstract: Described is a technique for optimization an image for facial detection. More specifically, described is a process of predicting the location of a face within an image and adjusting image settings based on at least a portion of the predicted location of the face. An image may be adjusted based on the characteristics of a metering region, which may be selected prior to performing facial detection. For example, the metering region may be a specified shape with dimensions equal to a certain percentage of the input image and placed at a specified location. The result of using such a metering region is that the image adjustments may be based on a portion of the face, and therefore, may be optimized for facial detection.
    Type: Grant
    Filed: February 3, 2016
    Date of Patent: January 1, 2019
    Assignee: Google LLC
    Inventor: Uriel Gerardo Rodriguez
  • Patent number: 10162433
    Abstract: The present disclosure illustrates an optical navigation apparatus with defocused image compensation function and a compensation circuit thereof. The optical navigation apparatus comprises a light source, an image sensing circuit and a compensation circuit. The light source is configured to illuminate a work surface. The image sensing circuit captures a first image related to the work surface. The compensation circuit is configured to transform the first image and a point spread function of the light source into a first conversion result and a second conversion result in frequency domain, respectively, and then transform a result multiplied by the first conversion result and a reciprocal of the second conversion result from frequency domain to time domain to generate a second image.
    Type: Grant
    Filed: May 16, 2016
    Date of Patent: December 25, 2018
    Assignee: PIXART IMAGING INC.
    Inventors: Guo-Zhen Wang, Hsuan-Ku Chen
  • Patent number: 10153001
    Abstract: In an embodiment, a method of creating a skimming preview of a video includes electronically receiving a plurality of video shots, analyzing each frame in a video shot from the plurality of video shots, where analyzing includes determining a saliency of each frame of the video shot. The method also includes determining a key frame of the video shot based on the saliency of each frame the video shot, extracting visual features from the key frame, performing shot clustering of the plurality of video shots to determine concept patterns based on the visual features, and generating a reconstruction reference tree based on the shot clustering. The reconstruction reference tree includes video shots categorized according to each concept pattern.
    Type: Grant
    Filed: October 26, 2015
    Date of Patent: December 11, 2018
    Assignee: Vid Scale, Inc.
    Inventors: Taoran Lu, Zheng Yuan, Yu Huang, Dapeng Oliver Wu, Hong Heather Wu
  • Patent number: 10143177
    Abstract: A system that includes a laser configured to generate a profile signal of at least a portion of a dairy livestock and a processor. The processor is configured to obtain the profile signal and detect one or more edge pair candidates in the profile signal, compare the complementary distance gradients of each of the one or more edge pair candidates to a minimum distance gradient length to be considered an edge pair, and identify an edge pair from among the one or more edge pair candidates as a teat candidate based on the comparison. The processor is further configured to determine position information for the teat candidate.
    Type: Grant
    Filed: March 2, 2018
    Date of Patent: December 4, 2018
    Assignee: Technologies Holdings Corp.
    Inventors: Mark A. Foresman, Bradley J. Prevost
  • Patent number: 10140495
    Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.
    Type: Grant
    Filed: October 3, 2016
    Date of Patent: November 27, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
  • Patent number: 10140731
    Abstract: An image processing apparatus that monochromatizes a gray pixel included in bitmap image data into black pixel includes: a detection unit configured to detect, in the case where a pixel of interest in the image data is a pixel constituting an edge, a pixel that exists in the vicinity of the pixel of interest and whose color is different from that of the pixel of interest; and a determination unit configured to determine a ratio of the processing to monochromatize into black for the pixel of interest that is a pixel constituting the edge based on the distance from the detected different color pixel.
    Type: Grant
    Filed: November 23, 2015
    Date of Patent: November 27, 2018
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Hitoshi Kakuta