Patents Examined by Vikkram Bali
  • Patent number: 9684973
    Abstract: A method is provided that includes acquiring, with a detector defining a field of view (FOV), emission imaging data of an object over the FOV. The method also includes determining, with one or more processing units, a volume of interest (VOI) of the emission imaging data, wherein the VOI defines a volume smaller than an imaged volume of the object. Further, the method includes performing, with the one or more processing units, a multivariate data analysis on the VOI to generate a waveform for the VOI. Also, the method includes determining, with the one or more processing units, an amount of motion for at least the VOI based on the waveform. The method further includes displaying, on a display unit, at least one of the amount of motion or an image reconstructed based on the emission imaging data.
    Type: Grant
    Filed: December 8, 2014
    Date of Patent: June 20, 2017
    Assignee: General Electric Company
    Inventor: Scott David Wollenweber
  • Patent number: 9672595
    Abstract: There is provided an ultrasound image processing apparatus which displays an ultrasonic image with a higher resolution. For each pixel of interest on a previous frame, a pattern matching process is applied between the previous frame and a current frame, to calculate, for each pixel of interest, a mapping address to the current frame as a movement destination or a two-dimensional movement vector. The mapping address includes an integer value and a fractional value. The current frame is re-constructed into a high-density frame including a plurality of interpolation lines based on an original group of pixels of the current frame and an additional group of pixels defined by a pixel value and the mapping address of each pixel of interest on the previous frame. In generation of the mapping address, a sub-pixel process is applied.
    Type: Grant
    Filed: November 1, 2011
    Date of Patent: June 6, 2017
    Assignee: Hitachi, Ltd.
    Inventor: Masaru Murashita
  • Patent number: 9672423
    Abstract: A method of tracking an object of an object tracking apparatus is provided. The method includes by performing probability propagation between a set of frames where tracking of a target object is completed and a set of frames where tracking of a target object is not completed among a plurality of frames of an image, calculating a probability map for a target object in each frame included the set of frames where tracking is completed, selecting a frame form the set of frames where tracking is not completed based on the calculated probability map, and determining a location of the target object in the selected frame.
    Type: Grant
    Filed: December 3, 2014
    Date of Patent: June 6, 2017
    Assignees: SAMSUNG ELECTRONICS CO., LTD., POSTECH ACADEMY-INDUSTRY FOUNDATION
    Inventors: Tae-gyu Lim, Bo-hyung Han, Woo-sung Shim, Su-ha Kwak, Seung-hoon Hong
  • Patent number: 9662062
    Abstract: A tool for recommending proper sun block use. The tool receives, by one or more computer processors, a first image of a user captured by a camera, and a second image of a user captured by a camera, wherein the first image is an ultraviolet image, and the second image is a digital color image. The tool determines, by one or more computer processors, areas of ultraviolet radiation vulnerability for the user captured in the first and second image. The tool determines, by one or more computer processors, a level of ultraviolet radiation vulnerability for the determined areas. The tool determines, by one or more computer processors, a recommendation for proper sun block use based, at least in part, on the level of ultraviolet radiation vulnerability.
    Type: Grant
    Filed: September 5, 2014
    Date of Patent: May 30, 2017
    Assignee: International Business Machines Corporation
    Inventors: Brian C. De Guia, Sandy Y. McDonald, Duy Q. Nguyen, Esperanza D. Rodriguez, Gary D. Williams
  • Patent number: 9665769
    Abstract: The method includes receiving, by one or more computer processors, data indicating a hand is on a touch-sensitive surface. The method further includes identifying, by one or more computer processors, a position of the hand. The method further includes determining, by one or more computer processors, a change in the position of the hand. The method further includes characterizing, by one or more computer processors, the change in position of the hand on the touch-sensitive surface. The method further includes generating, by one or more computer processors, an alphanumeric character based upon the characterized change in the position of the hand.
    Type: Grant
    Filed: August 18, 2015
    Date of Patent: May 30, 2017
    Assignee: International Business Machines Corporation
    Inventors: Cameron J. Bosnic, Jr., Derek M. Harden
  • Patent number: 9662061
    Abstract: A tool for recommending proper sun block use. The tool receives, by one or more computer processors, a first image of a user captured by a camera, and a second image of a user captured by a camera, wherein the first image is an ultraviolet image, and the second image is a digital color image. The tool determines, by one or more computer processors, areas of ultraviolet radiation vulnerability for the user captured in the first and second image. The tool determines, by one or more computer processors, a level of ultraviolet radiation vulnerability for the determined areas. The tool determines, by one or more computer processors, a recommendation for proper sun block use based, at least in part, on the level of ultraviolet radiation vulnerability.
    Type: Grant
    Filed: December 16, 2013
    Date of Patent: May 30, 2017
    Assignee: International Business Machines Corporation
    Inventors: Brian C. De Guia, Sandy Y. McDonald, Duy Q. Nguyen, Esperanza D. Rodriguez, Gary D. Williams
  • Patent number: 9655580
    Abstract: A method includes receiving, with at least one processor, a first projection dataset corresponding to X-rays at a first energy level projected towards a subject at a first set of view angles and receiving, with the at least one processor, a second projection dataset corresponding to X-rays at a second energy level projected towards the subject at a second set of view angles. The method further includes identifying, with the at least one processor, a metal trace from at least one of the first projection dataset and the second projection dataset. Moreover, the method includes converting, with the at least one processor, at least a portion of the first projection dataset to a pseudo dataset at the second energy level. The method also includes generating, with the at least one processor, a final image of the subject based on the second projection dataset, the pseudo dataset, and the metal trace.
    Type: Grant
    Filed: October 23, 2015
    Date of Patent: May 23, 2017
    Assignee: General Electric Company
    Inventors: Yannan Jin, Bruno Kristiaan Bernard De Man, Ge Wang, Yan Xi
  • Patent number: 9652850
    Abstract: A subject tracking device includes a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute, detecting at least one subject candidate area in which it is probable that a tracking target subject appears on an image that is received from an imaging unit; calculating a degree of blur of the subject candidate area for each of the subject candidate areas; determining that the subject appears in a subject candidate area having a degree of blur in accordance with a moving speed of the subject, out of the subject candidate areas; and deciding movement of the subject depending on a movement direction from an area in which the subject appears on a previous image that is captured by the imaging unit before capturing the image, to the subject candidate area in which the subject appears on the image.
    Type: Grant
    Filed: May 13, 2013
    Date of Patent: May 16, 2017
    Assignee: FUJITSU LIMITED
    Inventors: Akihiro Minagawa, Yutaka Katsuyama, Hiroaki Takebe, Yoshinobu Hotta, Masayoshi Shimizu
  • Patent number: 9646224
    Abstract: The present disclosure relates to an image processing method, an image processing device, and an automated optical inspection machine. The method includes: an inspection area determining step for determining a rectangular inspection area in an inspected image; a definition threshold determining step for calculating an image definition threshold according to the gray values of pixels of a plurality of sample images in the inspection area; a product image definition determining step for calculating a product image definition according to the gray values of pixels of a product image in the inspection area; and a comparison step for comparing the product image definition with the image definition threshold; and a product image selecting step for selecting the current product image as an image to be inspected.
    Type: Grant
    Filed: May 15, 2014
    Date of Patent: May 9, 2017
    Assignee: SHENZHEN CHINA STAR OPTOELECTRONICS TECHNOLOGY CO., LTD.
    Inventor: Yueyan Zhang
  • Patent number: 9628659
    Abstract: A machine vision system including a digital camera can be employed to inspect an object in a field of view, including capturing an original digital image including a multiplicity of pixels and associated light intensities for the field of view including the object. A bitmap image file is generated, and a mean value and a standard deviation of the light intensities of the multiplicity of pixels of the bitmap image file for the original digital image are dynamically determined. New image files are generated, each including a portion of the multiplicity of pixels having associated light intensities within a prescribed range of light intensities defined by the mean value and the standard deviation. Line segments are extracted from each of the new image files, and the extracted line segments from the new image files are merged and clustered to generate integral lines based thereon.
    Type: Grant
    Filed: January 8, 2015
    Date of Patent: April 18, 2017
    Assignee: GM Global Technology Operations LLC
    Inventors: Jaewoong Kim, Sukhan Lee, Jianying Shi
  • Patent number: 9626758
    Abstract: According to one embodiment, at least a portion of medical information of a patient is displayed within MRCS executed within a local device, the medical information including medical treatment history of the patient. At least a portion of the displayed medical information of the patient is transmitted to a medical imaging processing server over a network, where the transmitted medical information includes a patient identifier (ID) of the patient. Both the at least a portion of patient medical information and one or more medical images are displayed within the MRCS, where the medical images are associated with the patient and rendered by the medical image processing server. A set of icons representing a set of image processing tools is displayed within the MRCS, which when activated by a user, allow an image to be manipulated by the imaging processing server.
    Type: Grant
    Filed: November 4, 2014
    Date of Patent: April 18, 2017
    Assignee: TeraRecon, Inc.
    Inventors: Robert James Taylor, Tiecheng Zhao, Tim Frandsen
  • Patent number: 9615804
    Abstract: In a method for image generation and image evaluation in the medical field, raw data are generated by a selected medical modality, in particular a computed tomography scanner, depending on given modality parameters, and image data are generated from the raw data using an image reconstruction depending on given reconstruction parameters. The image data are evaluated by a given analysis application. Before acquiring the raw data, a secondary application automatically proposes a set of parameter values for the modality parameters and/or for the reconstruction parameters coordinated to the given analysis application and/or given patient information.
    Type: Grant
    Filed: June 25, 2012
    Date of Patent: April 11, 2017
    Assignee: Siemens Aktiengesellschaft
    Inventor: Michael Scheuering
  • Patent number: 9613480
    Abstract: A method for authenticating a tag, includes: a step (205) of capturing an image, with a communicating mobile terminal, of at least a portion of a tag having at least a portion of an identifier; a step (210) of transmitting the identifier to a server; a step (215) of reading, from a memory of tag images, the image of a tag having the identifier; a step (220) of transmitting, to the communicating mobile terminal, at least a portion of the image read from the memory; and a step (230) of displaying at least a portion of the transmitted image superimposed on an image captured by the terminal.
    Type: Grant
    Filed: June 21, 2012
    Date of Patent: April 4, 2017
    Assignee: ADVANCED TRACK & TRACE
    Inventors: Jean-Pierre Massicot, Zbigniew Sagan, Alain Foucou
  • Patent number: 9607366
    Abstract: A system uses machine learning techniques to train models for determining whether to activate high dynamic range (HDR) imaging in devices. The system may train machine learning components/models based on customized image metrics (such as customized histograms) that can be used across devices. The system may also train HDR systems on non-image data like GPS data, etc. to make improved HDR recommendations based on the context of a particular image.
    Type: Grant
    Filed: December 19, 2014
    Date of Patent: March 28, 2017
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Ilya Vladimirovich Brailovskiy, Igor Aleksandrovich Tryndin
  • Patent number: 9602796
    Abstract: Technologies for improving the accuracy of depth camera images include a computing device to generate a foreground mask and a background mask for an image generated by a depth camera. The computing device identifies areas of a depth image of a depth channel of the generated image having unknown depth values as one of interior depth holes or exterior depth holes based on the foreground and background masks. The computing device fills at least a portion of the interior depth holes of the depth image based on depth values of areas of the depth image within a threshold distance of the corresponding portion of the interior depth holes. Similarly, the computing device fills at least a portion of the exterior depth holes of the depth image based on depth values of areas of the depth image within the threshold distance of the corresponding portion of the exterior depth holes.
    Type: Grant
    Filed: May 20, 2013
    Date of Patent: March 21, 2017
    Assignee: Intel Corporation
    Inventors: Rohan Chandra, Abhishek Ranjan, Shahzad A. Malik
  • Patent number: 9594775
    Abstract: A system includes: receiving first information about a device, where the first information includes data corresponding to a location of the device and a time at which the device was at the location; identifying one or more images associated with second information that is within a range of the first information, where the second information for an image includes data corresponding to a location at which the image was captured and a time at which the image was captured, and where the location at which the image was captured and a time at which the image was captured are within a range of the location of the device and the time at which the device was at the location; and retrieving the one or more images associated with the second information.
    Type: Grant
    Filed: September 16, 2015
    Date of Patent: March 14, 2017
    Assignee: Google Inc.
    Inventor: Dean K. Jackson
  • Patent number: 9571698
    Abstract: A computer-implemented method for compressing a data set, the method comprising receiving a first data block of the data set, selecting automatically by a compression management module a compression module from a plurality of compression modules to apply to the first data block based on projected compression efficacy or resource utilization, and compressing the first data block with the selected compression module to generate a first compressed data block.
    Type: Grant
    Filed: March 30, 2012
    Date of Patent: February 14, 2017
    Assignee: EMC IP Holding Company LLC
    Inventors: Grant R. Wallace, Philip N. Shilane, Frederick Douglis, Jianqiang Luo
  • Patent number: 9569818
    Abstract: There is provided an ultrasound image processing apparatus which displays an ultrasonic image with a higher resolution. In a received frame, a first pixel array, a second pixel array, and a third pixel array are defined in depths different from each other. For each pixel of interest on the first pixel array, a pattern matching process is applied between the first pixel array and the second pixel array, to calculate a mapping address on the second pixel array for the pixel of interest. In addition, for each pixel of interest on the third pixel array, a pattern matching process is applied between the third pixel array and the second pixel array, to calculate a mapping address on the second pixel array for each pixel of interest. The second pixel array is re-constructed into a high-density pixel array using pixel values and mapping addresses of a plurality of pixels of interest.
    Type: Grant
    Filed: November 1, 2011
    Date of Patent: February 14, 2017
    Assignee: HITACHI, LTD.
    Inventor: Masaru Murashita
  • Patent number: 9560354
    Abstract: A method of predicting a motion vector for a current block in a current picture includes obtaining, by the moving picture decoding device, at least three motion vectors for at least three blocks other than the current block based on a direction of a reference picture, wherein the direction of the reference picture is based on a display order of the reference picture and a display order of the current picture, and the at least three blocks are not in an intra mode and predicting, by the moving picture decoding device, the motion vector for the current block by using a median operation of the at least three motion vectors.
    Type: Grant
    Filed: October 15, 2014
    Date of Patent: January 31, 2017
    Assignee: LG ELECTRONICS INC.
    Inventors: Byeong Moon Jeon, Yoon Seong Soh
  • Patent number: 9547795
    Abstract: An image based obstacle detection method. A camera mounted on a vehicle provides a set of image frames while the vehicle is in motion. The image frames define an image plane having a vertical aspect and a horizontal aspect. The relevancy of an object is determined by (i) selecting first and second feature points from the object that are spaced apart vertically in a first image frame; (ii) tracking the positions of the first and second feature points over at least a second image frame; and (iii) deciding the object to be relevant if the first and second feature points move dissimilar distances in physical space, within a tolerance, and deciding the object to be irrelevant otherwise. The motion of relevant objects is then estimated to determine if any relevant object is likely to become an obstacle to the vehicle.
    Type: Grant
    Filed: January 20, 2012
    Date of Patent: January 17, 2017
    Assignee: MAGNA ELECTRONICS INC.
    Inventor: Nikhil Gupta