Patents Examined by Eueng-nan Yeh
  • Patent number: 10237593
    Abstract: Monitoring quality of experience (QoE) using a no-reference (NR) method. An uncompressed audio/video (AV) stream is received from output of a device under test (DUT), where the uncompressed AV stream includes content that is known to be devoid of a set of one or more AV artifacts. At least one of the set of AV artifacts is automatically tested for its existence using a no-reference method that does not use a comparison to an input reference AV stream. Upon determining that there is an AV event representing one of the set of AV artifacts based on the automatic testing, a video clip that includes the AV event is automatically generated. The automatically generated video clip is stored.
    Type: Grant
    Filed: June 24, 2016
    Date of Patent: March 19, 2019
    Assignee: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
    Inventors: Anand Arun Joshi, Sandesh Kashikar, Bradley Holmes, Jose Maria Cubero
  • Patent number: 10217190
    Abstract: A method for reconstructing one or more high-resolution point spread functions (PSF) from one or more low-resolution images includes acquiring one or more low-resolution images of a wafer, aggregating the one or more low-resolution image patches, and estimating one or more sub-pixel shifts in the one or more low-resolution images and simultaneously reconstructing one or more high-resolution PSF from the aggregated one or more low-resolution image patches.
    Type: Grant
    Filed: December 27, 2016
    Date of Patent: February 26, 2019
    Assignee: KLA-Tencor Corporation
    Inventors: Helen Liu, Rohit Patnaik, Stephen Osborne
  • Patent number: 10210418
    Abstract: A method detects an object in an image. The method extracts a first feature vector from a first region of an image using a first subnetwork and determines a second region of the image by processing the first feature vector with a second subnetwork. The method also extracts a second feature vector from the second region of the image using the first subnetwork and detects the object using a third subnetwork on a basis of the first feature vector and the second feature vector to produce a bounding region surrounding the object and a class of the object. The first subnetwork, the second subnetwork, and the third subnetwork form a neural network. Also, a size of the first region differs from a size of the second region.
    Type: Grant
    Filed: July 25, 2016
    Date of Patent: February 19, 2019
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventors: Ming-Yu Liu, Oncel Tuzel, Amir massoud Farahmand, Kota Hara
  • Patent number: 10192132
    Abstract: A method and apparatus for extraction of dots in an image are described. An image is binarized according to an initial intensity threshold to obtain an initial binary image including foreground and background pixels. Each foreground pixel has a foreground intensity value and each background pixel has a background intensity value. A set of blobs including foreground pixels is selected from the initial binary image to be part of a selected set of dots, where each blob from the set of blobs has characteristics of a dot. Responsive to determining that a successive binarization is to be performed, the following operations are repeated: (1) binarization of the image according to a successive intensity threshold (2) selection of a successive set of blobs, where each blob has characteristics of a dot. Responsive to determining that a successive binarization is not to be performed, the selected set of dots is output.
    Type: Grant
    Filed: September 27, 2016
    Date of Patent: January 29, 2019
    Assignee: MATROX ELECTRONIC SYSTEMS LTD.
    Inventor: Dominique Rivard
  • Patent number: 10184837
    Abstract: The present invention relates to charts, stacks and methods for evaluating skin color of a mammalian subject. The chart may include a substrate and an indicia visible from a first side of the substrate that includes a plurality of images of mammalian skin tones having varying degrees of yellowness, wherein each indicia is correlated with an index value. Also, the present invention relates to packaged topical cosmetic products that include a skin chart as well as to methods for evaluating anti-aging and skin lightening products.
    Type: Grant
    Filed: November 22, 2016
    Date of Patent: January 22, 2019
    Assignee: ACCESS BUSINESS GROUP INTERNATIONAL LLC
    Inventors: Di Qu, Yulia Park
  • Patent number: 10186028
    Abstract: Gray level histograms for a test image and a reference image are adjusted by histogram scaling. Parameters from the histogram scaling are applied to the test image and the reference image. After the parameters are applied, the reference image and the test image are compared to produce a difference image, such as by subtracting the reference image from the test image. Noise in the difference image can be reduced, which improves defect identification in the difference image. In addition, noisy structures in the difference image which are elongated in vertical or horizontal direction can be found. If the noise exceeds a certain threshold, the structures may not be inspected.
    Type: Grant
    Filed: November 16, 2016
    Date of Patent: January 22, 2019
    Assignee: KLA-Tencor Corporation
    Inventors: Bjorn Brauer, James A. Smith
  • Patent number: 10187656
    Abstract: Provided are an image processing device capable of adjusting computational complexity, an image interpolation method, and an image encoding method. The image interpolation method includes selecting a horizontal interpolation filter having a first complexity, selecting a vertical interpolation filter having a second complexity, calculating pixel values of sub-pixels by performing an interpolation operation by using the selected horizontal and vertical interpolation filters, and generating interpolation information related to the selected horizontal interpolation filter and the selected vertical interpolation filter, wherein the first and second complexities are different from each other.
    Type: Grant
    Filed: June 8, 2016
    Date of Patent: January 22, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jung-yeop Yang, Ju-won Byun
  • Patent number: 10176400
    Abstract: A method and apparatus for locating dot text in an image are described. A set of dots is extracted. A determination of whether a first region of interest (ROI) including the set of dots satisfies selection criteria is performed, where the first region of interest is oriented based on results from a principal component analysis of the set of dots. Responsive to determining that the first ROI does not satisfy the selection criteria, performing the following: removing an outlier dot from the first set of dots to obtain a second set of dots; when the second ROI satisfies the selection criteria, outputting the second ROI as a location of the dot text in the image, and when the second region of interest does not satisfy the selection criteria, repeating the operations until a resulting ROI is determined to satisfy the selection criteria.
    Type: Grant
    Filed: September 27, 2016
    Date of Patent: January 8, 2019
    Assignee: MATROX ELECTRONIC SYSTEMS LTD.
    Inventor: Dominique Rivard
  • Patent number: 10163003
    Abstract: Certain embodiments involve recognizing combinations of body shape, pose, and clothing in three-dimensional input images. For example, synthetic training images are generated based on user inputs. These synthetic training images depict different training figures with respective combinations of a body pose, a body shape, and a clothing item. A machine learning algorithm is trained to recognize the pose-shape-clothing combinations in the synthetic training images and to generate feature descriptors describing the pose-shape-clothing combinations. The trained machine learning algorithm is outputted for use by an image manipulation application. In one example, an image manipulation application uses a feature descriptor, which is generated by the machine learning algorithm, to match an input figure in an input image to an example image based on a correspondence between a pose-shape-clothing combination of the input figure and a pose-shape-clothing combination of an example figure in the example image.
    Type: Grant
    Filed: December 28, 2016
    Date of Patent: December 25, 2018
    Assignee: Adobe Systems Incorporated
    Inventors: Zhili Chen, Duygu Ceylan, Byungmoon Kim, Liwen Hu, Jimei Yang
  • Patent number: 10152779
    Abstract: A system that incorporates the subject disclosure may include, for example, partitioning the image into a group of blocks, calculating principle bilateral filtered image components for a first subset of the group of blocks where the principle bilateral filtered image components are not calculated for a second subset of the group of blocks, and applying an infinite impulse response filter to the image using the principle bilateral filtered image components. Other embodiments are disclosed.
    Type: Grant
    Filed: October 26, 2016
    Date of Patent: December 11, 2018
    Assignee: AT&T Intellectual Property I, L.P.
    Inventors: Chao Tian, Shankar Krishnan
  • Patent number: 10152797
    Abstract: Presently disclosed is a method for co-segmenting three-dimensional models represented by sparse and low-rank feature, comprising: pre-segmenting each three-dimensional model of a three-dimensional model class to obtain three-dimensional model patches for the each three-dimensional model; constructing a histogram for the three-dimensional model patches of the each three-dimensional model to obtain a patch feature vector for the each three-dimensional model; performing a sparse and low-rank representation to the patch feature vector for the each three-dimensional model to obtain a representation coefficient and a representation error of the each three-dimensional model; determining a confident representation coefficient for the each three-dimensional model according to the representation coefficient and the representation error of the each three-dimensional model; and clustering the confident representation coefficient of the each three-dimensional model to co-segment the each three-dimensional model respectiv
    Type: Grant
    Filed: March 2, 2017
    Date of Patent: December 11, 2018
    Assignee: BEIHANG UNIVERSITY
    Inventors: Xiaowu Chen, Kan Guo, Qinping Zhao
  • Patent number: 10154262
    Abstract: An image processing apparatus comprising an acquiring unit configured to acquire an encoding target block having a plurality of groups each including a predetermined number of pixels, a deciding unit configured to decide for each group a quantization parameter used to quantize image data of the group and an encoding scheme so that a code length of the encoding target block does not exceed a predetermined value, wherein the deciding unit selects, as the encoding scheme of a respective group, either of a first encoding scheme that outputs quantized image data and a second encoding scheme that outputs encoded data of a differential between quantized image data and prediction data, and an encoding unit configured to generate encoded data by encoding image data of the encoding target block in accordance with the quantization parameters and the encoding schemes decided for the respective groups.
    Type: Grant
    Filed: April 26, 2016
    Date of Patent: December 11, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventors: Eishi Takeda, Yushi Kaneko
  • Patent number: 10147167
    Abstract: Generating a super-resolved reconstructed image includes acquiring a multitude of monochromatic images of a scene and extracting high-frequency band luma components from the acquired images. A high-resolution luma image is generated using the high-frequency components and motion data for the acquired images. The high-resolution luma image is combined with an up-sampled color image, generated from the acquired images, to generate a super-resolved reconstructed color image of the scene.
    Type: Grant
    Filed: November 14, 2016
    Date of Patent: December 4, 2018
    Assignee: Heptagon Micro Optics Pte. Ltd.
    Inventors: Florin Cutu, James Eilertsen
  • Patent number: 10116924
    Abstract: A mobile electronic device includes a transparent display screen for comparing and accurately determining the color of a predetermined object, for various applications, including augmented reality. Color data for a perceived color stores in a memory and displays images as perceived through the transparent display screen. Image difference values are determined between a first set of optical processing data and a second set of optical processing data. The transparent display screen indicates image difference values from including differences in color, texture, transparency, lighting, etc., especially for augmented reality applications. A memory stores optical processing data and optical processing instructions and algorithms. A computer processor executes optical processing instructions and algorithms and in response to optical processing data generated. An optical lens captures an image of an object for display on the transparent display screen.
    Type: Grant
    Filed: April 3, 2017
    Date of Patent: October 30, 2018
    Inventor: Suk K. Kim-Whitty
  • Patent number: 10107594
    Abstract: The present invention belongs to the technical field of spotting scopes, particularly to an analysis method for automatically analyzing a shooting accuracy, which is applied to an electronic spotting scope. The analysis method includes the following steps: converting an optical image obtained by a spotting scope into an electronic image, extracting a target paper area from the electronic image, and performing pixel-level subtraction on the target paper area and an electronic reference target paper to detect points of impact, calculating a center point of each of the points of impact, and determining a shooting accuracy according to a deviation of the center point of each of the points of impact and a center point of the target paper area. The analysis method provided by the present invention is simple and intuitive, facilitates the interpretation of a result, and does not need a system with too much artificial intervention to replace an existing monotonous high-error spotting system.
    Type: Grant
    Filed: November 24, 2017
    Date of Patent: October 23, 2018
    Assignee: Huntercraft Limited
    Inventors: Danyang Li, Ming Chen, Yayun Gong
  • Patent number: 10102632
    Abstract: A method for detecting line segments in an image. The method includes receiving an image taken by a camera. The method also includes computing, using a processor, line segment array metrics for the image. The method also includes finding, using the processor, a first maximum metric from the line segment array metrics. The method also includes determining, using the processor, a first line segment for the first maximum metric, wherein a processed image is created.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: October 16, 2018
    Assignee: The Boeing Company
    Inventor: Gary Alan Ray
  • Patent number: 10095951
    Abstract: During a description technique, a local descriptor for an object may be generated by computing a 2-dimensional histogram of pairs of angles between pairs of line segments that are aligned with edge pixels associated with the object. The pairs of line segments belong to a subset of k neighboring or proximate line segments. Moreover, this 2D histogram may represent the relative displacement and the relative orientations of the pairs of line segments in the subset as weights in bins or cells defined by angular quantization values, and the 2D histogram may exclude lengths of the line segments. Subsequently, the generated 2D histogram may be compared to predefined sets of descriptors in a model library that are associated with a set of objects, and the object may be identified as one of the set of objects based on a group of match scores determined in the comparisons.
    Type: Grant
    Filed: November 14, 2016
    Date of Patent: October 9, 2018
    Assignee: Datalogic IP Tech S.R.L.
    Inventors: Federico Tombari, Alessandro Franchi, Luigi Di Stefano
  • Patent number: 10096128
    Abstract: Provided is a change degree deriving device including a receiving unit that receives an image obtained by capturing a known color body and an object while focusing on the object, the known color body including plural of color samples, each of which has a known color numerical value, and a detection image, and a detecting unit that detects a focus deviation of the color samples in the image, based on the detection image.
    Type: Grant
    Filed: November 14, 2016
    Date of Patent: October 9, 2018
    Assignee: FUJI XEROX CO., LTD.
    Inventors: Shinji Sasahara, Hitoshi Ogatsu, Junichi Matsunoshita, Ken Ogino
  • Patent number: 10089743
    Abstract: A method for segmenting an image using a CNN including steps of: a segmentation device acquiring (i) a first segmented image for a t-th frame by a CNN_PREVIOUS, having at least one first weight learned at a t?(i+1)-th frame, segmenting the image, (ii) optical flow images corresponding to the (t?1)-th to the (t?i)-th frames, including information on optical flows from pixels of the first segmented image to corresponding pixels of segmented images of the (t?1)-th to the (t?i)-th frames, and (iii) warped images for the t-th frame by replacing pixels in the first segmented image with pixels in the segmented images referring to the optical flow images, (iv) losses by comparing the first segmented image with the warped images, (v) a CNN_CURRENT with at least one second weight obtained by adjusting the first weight to segment an image of the t-th frame and frames thereafter by using the CNN_CURRENT.
    Type: Grant
    Filed: October 5, 2017
    Date of Patent: October 2, 2018
    Assignee: StradVision, Inc.
    Inventors: Yongjoong Kim, Woonhyun Nam, Sukhoon Boo, Myungchul Sung, Donghun Yeo, Wooju Ryu, Taewoong Jang, Kyungjoong Jeong, Hongmo Je, Hojin Cho
  • Patent number: 10080028
    Abstract: A method of compensating for image compression errors is presented. The method comprises: receiving an image frame Fn during a frame period n, where n is a natural number; adding a compensation frame Cn to the image frame Fn to generate a compensated frame En; compressing the compensated frame En to generate a compressed frame CEn; decompressing the compressed frame CEn to generate a decompressed frame Dn; and subtracting the decompressed frame Dn from the compensated frame En to generate a next compensation frame Cn+1.
    Type: Grant
    Filed: November 17, 2015
    Date of Patent: September 18, 2018
    Assignee: Samsung Display Co., Ltd.
    Inventors: Ning Lu, Dihong Tian