Patents Examined by Gregory M. Desire
  • Patent number: 10390029
    Abstract: Systems and methods for improving efficiency in three-dimensional (3D) look-up table (LUT) coding and/or reducing table size of a 3D LUT may be provided. For example, octants associated with the 3D LUT may be provided for color space segmentation and coding may be performed on an octree associated with the octants where coding may include encoding nodes of the octree associated with the octants and corresponding vertices of the 3D LUT belonging to the nodes. The 3D LUT may also be signaled (e.g., based on a sequence and/or picture level).
    Type: Grant
    Filed: March 22, 2018
    Date of Patent: August 20, 2019
    Assignee: VID SCALE, Inc.
    Inventors: Yan Ye, Jie Dong, Yuwen He
  • Patent number: 10388051
    Abstract: A picture synthesis method and apparatus, an instant messaging method and a picture synthesis server/device are disclosed. The method comprises: after at least two pictures to be synthesized are acquired, determining a visual center of each of the pictures to be synthesized; cutting the corresponding pictures to be synthesized in accordance with the visual center of each of the pictures to be synthesized and a first set specification; and synthesizing all of the cut pictures to be synthesized to obtain a synthesized picture. Due to full consideration of the visual center of each of the pictures to be synthesized, a visual effect of the finally obtained synthesized picture is ensured, thereby improving the user experience.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: August 20, 2019
    Assignee: Alibaba Group Holding Limited
    Inventor: Puchao Feng
  • Patent number: 10387713
    Abstract: An apparatus for processing medical images includes a storage unit storing fingerprints that respectively correspond to a plurality of functions, a user input unit detecting a fingerprint of a user, and a controller performing a function corresponding to the detected fingerprint, from among the functions.
    Type: Grant
    Filed: October 27, 2017
    Date of Patent: August 20, 2019
    Assignee: SAMSUNG MEDISON CO., LTD.
    Inventors: Sun-mo Yang, Gil-ju Jin, Yu-ri Kim
  • Patent number: 10380763
    Abstract: A method includes acquiring, from a camera, an image frame including a representation of an object, and retrieving from a memory, data containing a template of a first pose of the object. A processor compares the first template to the image frame. A plurality of candidate locations in the image frame having a correlation with the template exceeding a predetermined threshold is determined. Edge registration on at least one candidate location of the plurality of candidate locations is performed to derive a refined pose of the object. Based at least in part on the performed edge registration, an initial pose of the object is determined, and a display image is output for display on a display device. The position at which the display image is displayed and/or the content of the display image is based at least in part on the determined initial pose of the object.
    Type: Grant
    Filed: November 16, 2017
    Date of Patent: August 13, 2019
    Assignee: SEIKO EPSON CORPORATION
    Inventors: Alex Levinshtein, Qadeer Baig, Andrei Mark Rotenstein, Yan Zhao
  • Patent number: 10379064
    Abstract: A substrate inspection device for inspecting a flexible printed board to determine whether the transparent adhesive material is properly applied thereto comprises: a substrate reading device which irradiates the flexible printed board with visible light to acquire image data; an adhesive material position determination unit which determines a position of adhesive material CAD data corresponding to the transparent adhesive material with respect to blue color image data among the image data corresponding to blue light which is readily absorbed by polyimide, to create adhesive material alignment data in which the adhesive material CAD data is superposed; an edge enhancing unit which performs processing, on the blue color image data, to enhance an edge of the transparent adhesive material; and a straight line determination unit which determines whether the edge of the transparent adhesive material is present in edge enhanced data in which the edge of the transparent adhesive material is enhanced.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: August 13, 2019
    Assignee: NIPPON MEKTRON, LTD.
    Inventor: Kenichi Mishima
  • Patent number: 10360693
    Abstract: The present disclosure provides a high resolution structured light system that is also capable of maintaining high throughput. The high resolution structured light system includes one or more image capture devices, such as a camera and/or an image sensor, a projector, and a blurring element. The projector is configured to project a binary pattern so that the projector can operate at high throughput. The binary projection pattern is subsequently filtered by the blurring element to remove high frequency components of the binary projection pattern. This filtering smoothes out sharp edges of the binary projection pattern, thereby creating a blurred projection pattern that changes gradually from the low value to the high value. This gradual change can be used by the structured light system to resolve spatial changes in the 3D profile that could not otherwise be resolved using a binary pattern.
    Type: Grant
    Filed: March 1, 2017
    Date of Patent: July 23, 2019
    Assignee: Cognex Corporation
    Inventors: Aaron Wallack, John Filhaber, George Costigan
  • Patent number: 10354162
    Abstract: A detected quadrilateral area is displayed and no group of candidate lines is displayed in a normal state. While a user is selecting a side that the user desires to change, a group of candidate lines corresponding to the selected side is displayed. Then, whether to replace a position of the selected side with a position of a candidate line is determined based on a movement destination position of the selected side.
    Type: Grant
    Filed: July 19, 2017
    Date of Patent: July 16, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Takashi Miyauchi
  • Patent number: 10346468
    Abstract: System and method for optically verified sample authentication are described herein.
    Type: Grant
    Filed: February 28, 2017
    Date of Patent: July 9, 2019
    Inventors: Vitaly Talyansky, Edward Talyansky, Jose Gasque
  • Patent number: 10346955
    Abstract: An image-filtering method that includes the steps outlined below is provided. Target image values and an input image having input pixel values are retrieved. A difference function between filtering response values of a desired output image and the target image values is determined, wherein the filtering response values are generated by filtering desired output pixel values of the desired output image based on characteristic filtering coefficients. An optimal solution of a desired output central pixel value of the desired output image is calculated according to a linear equation related to the characteristic filtering coefficients, wherein the optimal solution minimizes a value of the difference function. A corresponding relation between the desired output central pixel values and the input pixel values are retrieved from the optimal solution to calculate optimal filtering coefficients.
    Type: Grant
    Filed: June 13, 2017
    Date of Patent: July 9, 2019
    Assignee: REALTEK SEMICONDUCTOR CORPORATION
    Inventors: Tsung-Hsuan Li, Hao-Tien Chiang, Shih-Tse Chen
  • Patent number: 10346989
    Abstract: The invention relates to a method of calculating a displacement of an object of interest comprising a step of calculating (101) a displacement model of said object of interest from adjacent images of a set of pre-acquired images of said object of interest, said displacement model reflects the position of said object of interest along the time. The method is characterized in that the method further comprises the following. A step of determining (102) a first sub-set of images (S1) from said set of pre acquired images within one periodical time cycle of said set of pre-acquired images on the basis of the displacement model.
    Type: Grant
    Filed: December 11, 2015
    Date of Patent: July 9, 2019
    Assignee: Koninklijke Philips N.V.
    Inventors: Jingping Xu, Kongkuo Lu, William Tao Shi, Christopher Stephen Hall
  • Patent number: 10339423
    Abstract: The disclosed computer-implemented method for generating training documents used by classification algorithms may include (i) identifying a set of training documents used by a classification system to classify documents written in a first language, (ii) generating a list of tokens from within the training documents that indicate critical terms representative of classes defined by the classification system, (iii) translating the list of tokens from the first language to a second language, (iv) creating, based on the translated tokens, a set of simulated training documents that enables the classification system to classify documents written in the second language, and (v) classifying an additional document written in the second language based on the set of simulated training documents. Various other methods, systems, and computer-readable media are also disclosed.
    Type: Grant
    Filed: June 13, 2017
    Date of Patent: July 2, 2019
    Assignee: Symantec Corporation
    Inventors: Jonathan J. Dinerstein, Christian Larsen, Daniel Hardman
  • Patent number: 10339412
    Abstract: When searching for a registered image similar to a query image, an image processing apparatus estimates an area having a difference by comparing images determined to be similar if a plurality of similar images is found at the time of search of a similar image using an image feature amount in order to enhance search accuracy. Then, the image processing apparatus compares the query image with the plurality of images similar to the query image based on the difference area.
    Type: Grant
    Filed: January 31, 2017
    Date of Patent: July 2, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventors: Masahiro Matsushita, Hirotaka Shiiyama
  • Patent number: 10339689
    Abstract: Presented here is technology to efficiently process camera images to generate artistic images and videos using an artificial intelligence module receiving inputs from multiple sensors. Multiple sensors can include a depth sensor, a conventional camera, and a motion tracker providing inputs to the artificial intelligence module. Based on the inputs, the artificial intelligence module can segment the received image and/or video into a foreground image and a background image to produce portrait imagery by blurring the background image and/or video. The artificial intelligence module can select the most aesthetically pleasing image from a video. In addition, the artificial intelligence module can adjust lighting in an image or video to create artistic lighting effects. All the processing can be done in real time due to efficient combination of artificial intelligence modules, traditional image processing techniques, and use of specialized hardware.
    Type: Grant
    Filed: October 31, 2018
    Date of Patent: July 2, 2019
    Assignee: ESSENTIAL PRODUCTS, INC.
    Inventors: Xiaoyu Miao, Andrew E. Rubin
  • Patent number: 10339416
    Abstract: Embodiments of the present disclosure relate to systems, techniques, methods, and computer-readable mediums for one or more database systems configured to perform image identification of an image captured using a remote mobile device, and display of identity information associated with the captured image on the remote mobile device, in communication with the database system(s). A system obtains an image captured using a camera on a remote mobile device and performs image analysis to identify the captured image using reference images in one or more databases. The system can present the results for display an interactive user interface on the remote mobile device.
    Type: Grant
    Filed: July 5, 2018
    Date of Patent: July 2, 2019
    Assignee: Palantir Technologies Inc.
    Inventors: Aakash Goenka, Arzav Jain, Alexander Taheri, Daniel Isaza, Jack Zhu, William Manson, Vehbi Deger Turan, Stanislaw Jastrzebski
  • Patent number: 10339419
    Abstract: Methods, systems, and apparatus, for determining fine-grained image similarity. In one aspect, a method includes training an image embedding function on image triplets by selecting image triplets of first, second and third images; generating, by the image embedding function, a first, second and third representations of the features of the first, second and third images; determining, based on the first representation of features and the second representation of features, a first similarity measure for the first image to the second image; determining, based on the first representation of features and the third representation of features, a second similarity measure for the the first image to the third image; determining, based on the first and second similarity measures, a performance measure of the image embedding function for the image triplet; and adjusting the parameter weights of the image embedding function based on the performance measures for the image triplets.
    Type: Grant
    Filed: December 3, 2018
    Date of Patent: July 2, 2019
    Assignee: Google LLC
    Inventors: Yang Song, Jiang Wang, Charles J. Rosenberg
  • Patent number: 10327724
    Abstract: According to one or more embodiments, a method, a computer program product, and a computer system for detecting and characterizing aortic pathologies are provided. The method may include receiving, by a computer, one or more tomograph scan images corresponding to a patient's aorta. The one or more received tomograph scan images may be analyzed by the computer for one or more image features associated with one or more aortic pathologies, such as aortic dissection or an aortic aneurysm. One or more image features associated with the one or more aortic pathologies may be identified in the one or more analyzed tomograph scan images, which may allow the determination of an aortic pathology associated with the patient's aorta based on the identification of the image features. A portion of the aorta and one or more branch arteries corresponding to the determined aortic pathology may then be identified.
    Type: Grant
    Filed: October 10, 2017
    Date of Patent: June 25, 2019
    Assignee: International Business Machines Corporation
    Inventors: Ehsan Dehghan Marvast, Tanveer F. Syeda-Mahmood, Hongzhi Wang
  • Patent number: 10332263
    Abstract: An image processing device includes a division unit which divides an input image into a first content area and a first background area, a generation unit which corrects a first content area pixel included in the first content area by using a first peripheral pixel existing in the vicinity of the first content area among first background area pixels included in the first background area to generate a first background image formed with the after-correction first content area pixel and the first background area pixel, and a removal unit which removes the first background image from the input image.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: June 25, 2019
    Assignee: PFU LIMITED
    Inventors: Hiroki Tanizaki, Kiyoto Kosaka
  • Patent number: 10325137
    Abstract: A ridge flow based fingerprint image quality determination can be achieved independent of image resolution, can be processed in real-time and includes segmentation, such as fingertip segmentation, therefore providing image quality assessment for individual fingertips within a four finger flat, dual thumb, or whole hand image. A fingerprint quality module receives from one or more scan devices ridge-flow-containing imagery which can then be assessed for one or more of quality, handedness, historical information analysis and the assignment of bounding boxes.
    Type: Grant
    Filed: August 24, 2018
    Date of Patent: June 18, 2019
    Assignee: AWARE, INC.
    Inventors: James M. Maurer, L. Scott Hills
  • Patent number: 10319077
    Abstract: An image processing method is provided. The method includes the steps of: receiving upper image data; calculating a first ratio using a target pixel and a plurality of first reference pixels in the upper image data; calculating a first diffusion coefficient according to the first ratio and a diffusion coefficient mapping equation; calculating a first pixel value of the target pixel according to the target pixel, the first reference pixels, and the first diffusion coefficient; receiving lower image data; calculating a second ratio using the target pixel and a plurality of second reference pixels in the lower image data, wherein the target pixel has the first pixel value; calculating a second diffusion coefficient according to the second ratio and the diffusion coefficient mapping equation; and calculating a second pixel value of the target pixel according to the target pixel, the second reference pixels, and the second diffusion coefficient.
    Type: Grant
    Filed: September 7, 2016
    Date of Patent: June 11, 2019
    Assignee: SILICON OPTRONICS, INC.
    Inventor: Chun-Hung Lin
  • Patent number: 10311318
    Abstract: A reference line setting device includes an image acquisition means to acquire an image containing a character region, a recognition means to recognize characters from the character region of the image by a specified recognition method, a line position information acquisition means to acquire line position information of a plurality of characters out of the characters recognized by the recognition means with reference to a storage means storing, for each character, line position information concerning a position which at least two reference lines pass through in a vertical direction of characters, the reference lines being lines drawn in an alignment direction of characters, along which a certain part of each character is to be placed, and a setting means to set each of the reference lines to the image based on a plurality of line position information for each reference line acquired by the line position information acquisition means.
    Type: Grant
    Filed: July 17, 2015
    Date of Patent: June 4, 2019
    Assignee: Rakuten, Inc.
    Inventors: Ryota Hinami, Naoki Chiba