Patents Examined by Jingge Wu
  • Patent number: 10115199
    Abstract: Techniques, systems, and devices are disclosed for analyzing a reconstructed charged particle image of a volume of interest from charged particle detector measurements to determine a location and boundaries of one or more objects or an orientation of the one or more objects. The technique can include performing a segmentation operation on the reconstructed charged particle image of the volume. The segmentation operation identifies a subset of a set of voxels of the image of the volume as object candidate voxels. The technique can include locating corners of the one or more objects to determine the location, boundaries, or the orientation of the one or more objects. The technique can also include the computation of the center of mass of the one or more objects. The technique can include performing a morphological operation on the image and can include performing a connected-component analysis on the identified object-candidate voxels.
    Type: Grant
    Filed: October 6, 2015
    Date of Patent: October 30, 2018
    Assignee: Decision Sciences International Corporation
    Inventor: Rohit Patnaik
  • Patent number: 10110781
    Abstract: Systems and methods for restoring the appearances of scans of damaged physical documents. Ink bleed is removed and/or ink added to portions of a scanned image based on determining an ink bleed model by analyzing colors of pixels in the scanned image. Gaps in strokes are reconstructed based on analyzing pixel color at multiple angles around individual pixels in the scanned image to determine whether the individual pixels are part of a stroke. The appearance of the scanned image is also enhanced by comparing pixels that are not already close to a background color or ink color with other nearby pixels and, based on the nearby pixels, adjusting colors of the pixels that are not already close to the background color or ink color. These techniques are used individually or in combination to improve the appearance of the scanned image.
    Type: Grant
    Filed: June 23, 2016
    Date of Patent: October 23, 2018
    Assignee: Adobe Systems Incorporated
    Inventor: Andrew Marc Greene
  • Patent number: 10102432
    Abstract: Disclosed is an image recognition method including: producing a distribution of first pixel value range by acquiring a distribution of pixel values of a plurality of pixels of a first selected block in a first surveillance image from previous M images; producing a distribution of second pixel value range by acquiring a distribution of pixel values of the pixels of the first selected block from previous N images, wherein N and M are positive integers, and N<M; obtaining a first varying parameter related to the first selected block according to the distribution of first pixel value range and the distribution of second pixel value range; and generating a first recognition signal when the first varying parameter is greater than a first threshold.
    Type: Grant
    Filed: December 9, 2016
    Date of Patent: October 16, 2018
    Assignee: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
    Inventors: Denis Xynkin, Min-Hao Li, Yi-Yi Huang
  • Patent number: 10095946
    Abstract: The present disclosure is directed to systems and methods for strike through detection and, more particularly, to systems and methods for detecting a strike through in an address block of a mailpiece. The method is implemented in a computing device and includes: generating edges of lines within a text block identified through optical character recognition processes; locating text lines within the text block; characterizing the edges within the text lines and outside of the text lines; and grouping identified edges of the characterized edges outside of the text lines into co-linear groups.
    Type: Grant
    Filed: July 7, 2016
    Date of Patent: October 9, 2018
    Assignee: LOCKHEED MARTIN CORPORATION
    Inventors: Richard C. Vanhall, Robert S. Lunt, IV
  • Patent number: 10074190
    Abstract: A method includes obtaining at least a first energy dependent spectral image volume and a second different energy dependent spectral image volume from reconstructed spectral image data. The method further includes generating a multi-dimensional spectral diagram that maps, for each voxel, a value of the first energy dependent spectral image volume to a corresponding value of the second energy dependent spectral image volume. The method further includes generating a set of spectral texture analysis weights from the multi-dimensional spectral diagram. The method further includes retrieving a set of texture analysis functions, which are generated as a function of voxel intensity and voxel gradient value from a co-occurrence matrix histogram. The method further includes generating a texture analysis map through a texture analysis of the reconstructed spectral image data with the set of texture analysis functions and the set of spectral texture analysis weights and visually presenting the texture analysis map.
    Type: Grant
    Filed: October 30, 2015
    Date of Patent: September 11, 2018
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventor: Raz Carmi
  • Patent number: 10062165
    Abstract: A borderline extraction element 15 extracts a borderline B of adjacent vertebrae from an X-ray image on which multiple vertebrae are projected connected in a line. A vertebral area setting element 17 sets a area sandwiched by the adjacent borderlines B as a vertebral area and an area number is put to the respective vertebral areas L. When the vertebral areas are erroneously set up, a setup data erase element 21 erases the data of the vertebral areas L and the area number when the borderline is corrected. The setup data are erased, so that the borderline B can be shift-corrected to any location. A vertebral area setting element 17 resets the vertebral area L based on the location of the corrected borderline. Accordingly, the respective vertebral areas L are set up to the accurate locations and only the borderline B extracted to the wrong location is shift-corrected and the vertebral areas are reset. The work-burden to the operator for setting the vertebral area can be largely lessened.
    Type: Grant
    Filed: October 29, 2014
    Date of Patent: August 28, 2018
    Assignee: SHIMADZU CORPORATION
    Inventors: Tomohiro Nakaya, Daisuke Notohara
  • Patent number: 10049441
    Abstract: A method for classifying defects of a wafer, the method is executed by a computerized system, the method may include obtaining defect candidate information about a group of defect candidates, wherein the defect candidate information comprises values of attributes per each defect candidate of the group; selecting, by a processor of the computerized system, a selected sub-group of defect candidates in response to values of attributes of defect candidates that belong to at least the selected sub-group; classifying defect candidates of the selected sub-group to provide selected sub-group classification results; repeating, until fulfilling a stop condition: selecting an additional selected sub-group of defect candidates in response to (a) values of attributes of defect candidates that belong to at least the additional selected sub-group; and (b) classification results obtained from classifying at least one other selected sub-group; and classifying defect candidates of the additional selected sub-group to provide a
    Type: Grant
    Filed: February 9, 2016
    Date of Patent: August 14, 2018
    Assignee: APPLIED MATERIALS ISRAEL LTD.
    Inventors: Saar Shabtay, Idan Kaizerman, Amir Wachs
  • Patent number: 10049257
    Abstract: A fingerprint identification module includes a cover plate, a fingerprint identification sensor, at least one light source, a plurality of fibers, and a display device. The cover plate has an inner surface and an outer surface opposite to the inner surface. The fingerprint identification sensor and the at least one light source are located under the inner surface, and the at least one light source is located adjacent to the fingerprint identification sensor. The fibers are arranged in an array and are located between the cover plate and the fingerprint identification sensor. Each of the fibers has a light incident surface facing the inner surface and inclined relative to the inner surface. An optical axis of each of the fibers is perpendicular to the inner surface of the cover plate. The display device is located between the cover plate and the plurality of fibers.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: August 14, 2018
    Assignee: Gingy Technology Inc.
    Inventors: Jen-Chieh Wu, Chuck Chung
  • Patent number: 10032077
    Abstract: Various technologies pertaining to identification of vehicle tracks in synthetic aperture radar coherent change detection image data are described herein. Coherent change detection images are analyzed in a parameter space using Radon transforms. Peaks of the Radon transforms correspond to features of interest, including vehicle tracks, which are identified and classified. New coherent change detection images in which the features of interest and their characteristics are signified are then generated using inverse Radon transforms.
    Type: Grant
    Filed: October 29, 2015
    Date of Patent: July 24, 2018
    Assignee: National Technology & Engineering Solutions of Sandia, LLC
    Inventor: James G. Chow
  • Patent number: 10024774
    Abstract: A hardness tester includes a memory storing, as a parts program, definitions of measurement conditions including a coordinate system and test position defined with respect to an image of a standard reference sample; a pattern searcher performing a pattern searching process, with reference to a plurality of samples to be measured, using a pattern image based on the image of the standard reference sample, and detecting a number of samples having a shape identical to that of the standard reference sample, as well as a position and angle of the samples having the identical shape; a pattern definer defining a coordinate system and test position for each of the samples having the identical shape based on the position and angle of each of the samples having the identical shape; and a measurer measuring the hardness of the samples for which the coordinate system and test position have been defined.
    Type: Grant
    Filed: September 2, 2016
    Date of Patent: July 17, 2018
    Assignee: MITUTOYO CORPORATION
    Inventors: Fumihiko Koshimizu, Makoto Kaieda, Akira Takada
  • Patent number: 10013739
    Abstract: An embodiment of an image enhancement method is introduced for use in an electronic device. An image composed of a plurality of pixel values is first received, and each pixel therein is separated into two channels. The image is further divided into a plurality of blocks. A distribution of a selected channel is determined for each block, which is selected from the two channels. For each pixel, the pixel value of the selected channel is adjusted according to at least one distribution corresponding to at least one neighboring block. For each pixel, the pixel value of the other channel is adjusted according to the adjusted pixel value of the selected channel. As a result, the adjusted image is provided.
    Type: Grant
    Filed: August 26, 2016
    Date of Patent: July 3, 2018
    Assignee: HTC CORPORATION
    Inventors: Chia Yen Michael Lin, Chia-Ho Pan, Jing-Lung Wu, Hsin-Ti Chueh
  • Patent number: 10009615
    Abstract: The present invention concerns a method of encoding an image, the image comprising a plurality of coding elements made of blocks of pixels, each block of pixels being encoded according to a coding mode out of a plurality of coding modes, the method comprising for each block of pixel to be encoded determining the coding mode to be used for the encoding of a given block of pixels by sequentially evaluating some coding modes in the plurality of coding modes; wherein the method comprises evaluating Inter coding modes and fast IBC coding modes; and no residue-test is conducted between the evaluation of the Inter coding mode and the evaluation of the fast IBC mode. Accordingly, some good predictors may be found more rapidly and the whole encoding process is speed up.
    Type: Grant
    Filed: October 2, 2015
    Date of Patent: June 26, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventors: Christophe Gisquet, Guillaume Laroche, Patrice Onno
  • Patent number: 10007845
    Abstract: An eye state detecting method, applied to an electronic apparatus with an image sensor, comprising: (a) defining a detecting range according to a possible location of a user's eye, wherein the detecting range is smaller than a maximum detecting range that the electronic apparatus can apply; (b) capturing a detecting image via the detecting range; and (c) determining whether the user's eye is in an opening state or in a closing state according a brightness of to the detecting image. The present invention also discloses a method applying a smaller determining range to determine if the user's eye is open or close.
    Type: Grant
    Filed: June 30, 2016
    Date of Patent: June 26, 2018
    Assignee: PixArt Imaging Inc.
    Inventor: Guo-Zhen Wang
  • Patent number: 10002283
    Abstract: The present disclosure relates to an apparatus, a method, and an electronic device. The apparatus includes a display screen; a processor; a fingerprint sensor configured to acquire fingerprint data, wherein the fingerprint sensor is located in a content displaying area of the display screen; and a data transmission line configured to transmit the fingerprint data from the fingerprint sensor to the processor, wherein the data transmission line includes a first end connected to the fingerprint sensor and a second end connected to the processor.
    Type: Grant
    Filed: May 16, 2016
    Date of Patent: June 19, 2018
    Assignee: Xiaomi Inc.
    Inventors: Guosheng Li, Anyu Liu, Shanrong Liu
  • Patent number: 9996752
    Abstract: A method and system associated with a camera view of a moving-object in a scene. The method comprises detecting and tracking the moving object over multiple video frames, estimating an orientation of the moving object in each of the video frames, and constructing a cost map from the estimated orientations over the multiple video frames for finding a minimum cost path over the cost map. The Method also comprises determining regularized orientation estimates of the moving-object from the minimum cost path, and locating the vanishing point of the camera view based on an axis of the moving-object from the minimum cost path, the axis formed by using the regularized orientation estimates.
    Type: Grant
    Filed: August 30, 2016
    Date of Patent: June 12, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventors: Quang Tuan Pham, Geoffrey Richard Taylor
  • Patent number: 9984471
    Abstract: Systems of the present disclosure allow fields and labels to be identified in a digital image of a form without performing OCR. A digital image of a form can be partitioned into image segments using computer-vision image-segmentation techniques. Features for each image segment can be extracted using computer-vision feature-detection methods. The features extracted from an image segment can be included in an input instance for a machine-learning model. The machine-learning model can assign a classification to the input instance. The classification can associate the input instance with a field type or a label type.
    Type: Grant
    Filed: July 26, 2016
    Date of Patent: May 29, 2018
    Assignee: INTUIT INC.
    Inventors: Richard J. Becker, Pallavika Ramaswamy, Daniel L. Moise, Sheldon Porcina
  • Patent number: 9977997
    Abstract: Disclosed are a training method and apparatus for a CNN model, which belong to the field of image recognition. The method comprises: performing a convolution operation, maximal pooling operation and horizontal pooling operation on training images, respectively, to obtain second feature images; determining feature vectors according to the second feature images; processing the feature vectors to obtain category probability vectors; according to the category probability vectors and an initial category, calculating a category error; based on the category error, adjusting model parameters; based on the adjusted model parameters, continuing the model parameters adjusting process, and using the model parameters when the number of iteration times reaches a pre-set number of times as the model parameters for the well-trained CNN model. After the convolution operation and maximal pooling operation on the training images on each level of convolution layer, a horizontal pooling operation is performed.
    Type: Grant
    Filed: April 12, 2017
    Date of Patent: May 22, 2018
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Xiang Bai, Feiyue Huang, Xiaowei Guo, Cong Yao, Baoguang Shi
  • Patent number: 9977976
    Abstract: Disclosed herein is a method that improves the performance of handwriting recognition by calculating path scores so as to identify the path with the highest score as the basis for interpreting handwritten characters. Specifically, the method comprises the following steps: detecting connected regions in an input image comprising handwritten characters; determining a plurality of segmentation positions of the input image; obtaining a plurality of recognition results for each segment of each path in the input image, wherein each recognition result represents a character candidate for the segment and each path comprises one or more segments; obtaining a plurality of scores corresponding to the recognition results; calculating scores for each path in the input image based on segment lengths and the scores corresponding to the recognition results; and using the path with the highest score to interpret the handwritten characters in the input image.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: May 22, 2018
    Assignee: KONICA MINOLTA LABORATORY U.S.A., INC.
    Inventor: Duanduan Yang
  • Patent number: 9972081
    Abstract: The present teaching relates to surgical procedure assistance. In one example, a first volume of air inside a lung is obtained based on a first image of the lung captured prior to a surgical procedure. The lung has a first shape on the first image. A second volume of air deflated from the lung is determined based on a second image of the lung captured during the surgical procedure. A second shape of the lung is estimated based on the first shape of the lung and the first air volume inside the lung and second volume of air deflated from the lung. A surgical plan is updated based on the estimated second shape of the lung.
    Type: Grant
    Filed: October 29, 2015
    Date of Patent: May 15, 2018
    Assignee: EDDA TECHNOLOGY, INC.
    Inventors: Guo-Qing Wei, Li Fan, Cheng-Chung Liang, Jianzhong Qian, Xiaolan Zeng
  • Patent number: 9953242
    Abstract: The techniques described herein may identify images that likely depict one or more items by comparing features of the items to features of different regions-of-interest (ROIs) of the images. When a user requests to identify images that depict a particular item, the techniques may determine a region-of-interest (ROI) size based on the size of the requested item. The techniques may then search multiple images using the ROI size.
    Type: Grant
    Filed: December 21, 2015
    Date of Patent: April 24, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Ambrish Tyagi, David Allen Fotland