Patents Examined by Yon J. Couso
  • Patent number: 10997409
    Abstract: Techniques are described for using machine learning (ML) models to create information technology (IT) infrastructures at a service provider network based on image of IT system architecture diagrams. To create IT system architecture diagrams, system architects often use tools ranging from pen and paper and whiteboards to various types of software-based drawing programs. Based on a user-provided image of an IT system architecture diagram (for example, a digital scan of a hand drawn system diagram, an image file created by a software-based drawing program, or the like), a service provider network uses one or more ML models to analyze the image to identify the constituent elements of the depicted IT system architecture and to create an infrastructure template that can be used to automatically provision corresponding computing resources at the service provider network.
    Type: Grant
    Filed: June 6, 2018
    Date of Patent: May 4, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Sandeep Krishnamurthy, Rajankumar Singh, Aaron Markham, Lai Wei
  • Patent number: 10997704
    Abstract: A method for displaying a sequence of review images related to a structure, said method comprising: receiving (501) a review target (313) for the structure and an environmental factor (305) affecting at least one property of the structure; selecting (503), from a plurality of captured images related to the structure, a plurality (321) of review images of at least a part of the structure based on the review target, the environmental factor and position information associated with the review images with respect to the structure; and causing a display device to display the selected review images ordered according to the review target to form the sequence of review images.
    Type: Grant
    Filed: November 28, 2017
    Date of Patent: May 4, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventors: Julie Rae Kowald, Nicholas Grant Fulton
  • Patent number: 10997724
    Abstract: A method for image segmentation includes receiving an input image (102). The method further includes obtaining a deep learning model (104) having a triad of predictors (116, 118, 120). Furthermore, the method includes processing the input image by a shape model in the triad of predictors (116, 118, 120) to generate a segmented shape image (110). Moreover, the method includes presenting the segmented shape image via a display unit (128).
    Type: Grant
    Filed: December 14, 2017
    Date of Patent: May 4, 2021
    Assignee: General Electric Company
    Inventors: Hariharan Ravishankar, Vivek Prabhakar Vaidya, Sheshadri Thiruvenkadam, Rahul Venkataramani, Prasad Sudhakar
  • Patent number: 10991106
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for on-shelf merchandise detection are provided. One of the methods includes: obtaining a plurality of depth images associated with a shelf from a first camera; obtaining a plurality of images from one or more second cameras associated with each of a plurality of tiers of the shelf; detecting motions of a user's hand comprising reaching into and moving away from the shelf; determining one of the tiers of the shelf associated with the detected motions, a first point of time associated with reaching into the shelf, and a second point of time associated with moving away from the shelf; identifying a first image captured before the first point in time and a second image captured after the second point in time; and comparing the first image and the second image to determine one or more changes to merchandise.
    Type: Grant
    Filed: May 15, 2020
    Date of Patent: April 27, 2021
    Assignee: ADVANCED NEW TECHNOLOGIES CO., LTD.
    Inventors: Xiaobo Zhang, Zhangjun Hou, Xudong Yang, Xiaodong Zeng
  • Patent number: 10991117
    Abstract: A method of performing loop closure detection is described. The method comprises detecting a movement of a device having a camera; and adaptively disabling or enabling, using a processor of the device, a loop closure detection of the device based upon the detected movement of the device.
    Type: Grant
    Filed: December 23, 2018
    Date of Patent: April 27, 2021
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Siddharth K. Advani, Manish Goel, Sourabh Ravindran
  • Patent number: 10976656
    Abstract: A defect inspection device includes an image sensor configured to obtain an image of a target region of an object and divide the image of the target region into an array of pixels, and a processor. The processor is configured to receive a signal indicating a value of a property of the divided image, select a first pixel in the divided image, determine the value of the property of the first pixel, determine a reference pixel value for the first pixel, compare the reference pixel value to the value of the first pixel to obtain a difference value, and set a threshold difference at which a defect is assessed to be present, based at least in part on the value of the property of second pixels in the divided image adjacent to the first pixel.
    Type: Grant
    Filed: August 31, 2018
    Date of Patent: April 13, 2021
    Assignee: TOSHIBA MEMORY CORPORATION
    Inventor: Ryoji Yoshikawa
  • Patent number: 10963730
    Abstract: Comparing extracted card data from a continuous scan comprises receiving, by one or more computing devices, a digital scan of a card; obtaining a plurality of images of the card from the digital scan of the physical card; performing an optical character recognition algorithm on each of the plurality of images; comparing results of the application of the optical character recognition algorithm for each of the plurality of images; determining if a configured threshold of the results for each of the plurality of images match each other; and verifying the results when the results for each of the plurality of images match each other. Threshold confidence level for the extracted card data can be employed to determine the accuracy of the extraction. Data is further extracted from blended images and three-dimensional models of the card. Embossed text and holograms in the images may be used to prevent fraud.
    Type: Grant
    Filed: December 5, 2018
    Date of Patent: March 30, 2021
    Assignee: Google LLC
    Inventors: Sanjiv Kumar, Henry Allan Rowley, Xiaohang Wang, Yakov Okshtein, Farhan Shamsi, Alessandro Bissacco
  • Patent number: 10950008
    Abstract: A method that includes obtaining, using a processor, image data from a target coating. The method also includes performing, using the processor, an image analysis to determine at least one sparkle point from the image data, and performing, using the processor, a hue analysis to determine a sparkle color from the sparkle point. The method further includes calculating, using the processor, a sparkle color distribution, and generating, using the processor, a coating formulation that is the same or substantially similar in appearance to the target coating.
    Type: Grant
    Filed: October 23, 2019
    Date of Patent: March 16, 2021
    Assignee: PPG Industries Ohio, Inc.
    Inventors: Paul M. Beymore, A'Lisa Marie Krawciw
  • Patent number: 10931948
    Abstract: An image encoder includes a processor and a memory. The memory includes instructions configured to cause the processor to perform operations. In one example implementation, the operations may include determining whether a dictionary item is available for replacing a block of an image being encoded, the determining based on a hierarchical lookup mechanism, and encoding the image along with reference information of the dictionary item in response to determining that the dictionary item is available. In one more example implementation, the operations may include performing principal component analysis (PCA) on a block to generate a corresponding projected block, the block being associated with a group of images, comparing the projected block with a corresponding threshold, descending the block recursively based on the threshold until a condition is satisfied, and identifying a left over block as a cluster upon satisfying of the condition.
    Type: Grant
    Filed: May 21, 2018
    Date of Patent: February 23, 2021
    Assignee: Google LLC
    Inventors: Krzysztof Potempa, Jyrki Alakuijala, Robert Obryk
  • Patent number: 10922812
    Abstract: An image processing apparatus according to an embodiment has processing circuitry configured to acquire three-dimensional medical image data; set coordinates of at least two or more elements to evaluate an evaluation target represented by the three-dimensional medical image data, on images of different positioning slices of the three-dimensional medical image data; calculate a measured value for evaluating the evaluation target based on the coordinates; and control a display to display the measured value.
    Type: Grant
    Filed: June 6, 2018
    Date of Patent: February 16, 2021
    Assignee: CANON MEDICAL SYSTEMS CORPORATION
    Inventors: Yoshimasa Kobayashi, Hisanori Kato
  • Patent number: 10922796
    Abstract: A method of converting a wide dynamic range (WDR) image to a low dynamic range (LDR) image have the steps of: (i) obtaining a transfer function that has a plurality of sub-functions, each sub-function corresponding to a non-overlapped input interval of the dynamic range of the WDR image; (ii) determining the intensity of each pixel of the LDR image by using the transfer function and at least the intensity value of the corresponding pixel of the WDR image; and (iii) outputting the LDR image.
    Type: Grant
    Filed: July 11, 2017
    Date of Patent: February 16, 2021
    Assignee: TONETECH INC.
    Inventors: Orly Yadid-Pecht, Jie Yang, Alain Hore, Ulian Shahnovich
  • Patent number: 10922805
    Abstract: Provided are a microneedle array imaging device, a microneedle array imaging method, a microneedle array inspection device, and a microneedle array inspection method which enable inspection of a microneedle array with high accuracy based on an obtained image. A microneedle array 1 is imaged from a side of a surface on which microneedles 2 are arranged by irradiating a surface on a side opposite to the surface on which the microneedles 2 are arranged with parallel light as illumination light. At this time, the surface is irradiated with the illumination light under conditions in which an incident angle ? of light onto a bottom surface 2a of the microneedle 2 is 90??° or greater and an incident angle ? of light onto a side surface 2b of the microneedle 2 is less than a critical angle ?. In this manner, a state in which almost no light is emitted from a tip portion of the microneedle 2 can be generated.
    Type: Grant
    Filed: February 25, 2019
    Date of Patent: February 16, 2021
    Assignee: FUJIFILM Corporation
    Inventors: Takashi Murooka, Kazuo Onishi
  • Patent number: 10912444
    Abstract: In order to acquire height information regarding a subject disposed on the internal surface of an elongated tubular member, an image processing apparatus according to the present disclosure, includes a processor the processor including hardware and configured to perform the steps of receiving a first image and a second image acquired from a subject using an optical system having a field of view in a direction of at least about 90° to a central axis of the optical system, the first image acquired at a first position, the second image acquired at a second position, the second position different from the first position along the central axis; and calculating a distance between the subject and the central axis of the optical system, based on a distance between the first position and the second position, and based on the corresponding points in the third image and in the fourth image.
    Type: Grant
    Filed: August 22, 2018
    Date of Patent: February 9, 2021
    Assignee: OLYMPUS CORPORATION
    Inventor: Ikutoshi Fukushima
  • Patent number: 10902582
    Abstract: A method, system and computer readable medium for providing information about a region of a sample. The method includes (i) obtaining, by an imager, multiple images of the region; wherein the multiple images differ from each other by at least one parameter (ii) receiving or generating multiple reference images; (iii) generating multiple difference images that represent differences between the multiple images and the multiple reference images; (iv) calculating a set of region pixel attributes, (v) calculating a set of noise attributes, based on multiple sets of region pixels attributes of the multiple region pixels; and (vi) determining for each region pixel, whether the region pixel represents a defect based on a relationship between the set of noise attributes and the set of region pixel attributes of the pixel.
    Type: Grant
    Filed: January 17, 2019
    Date of Patent: January 26, 2021
    Assignee: Applied Materials Israel, Ltd.
    Inventors: Haim Feldman, Eyal Neistein, Harel Ilan, Shahar Arad, Ido Almog
  • Patent number: 10902622
    Abstract: A method of generating a vehicle environment view for a vehicle, having has the following steps. Camera images are provided by vehicle cameras on the body of the vehicle. A vehicle environment view is calculated based on the camera images. A texture of a ground surface that is located below the vehicle body and is not visible to the cameras, is determined within the vehicle environment view by performing a local color prediction and a movement-compensated texture prediction.
    Type: Grant
    Filed: September 21, 2017
    Date of Patent: January 26, 2021
    Assignee: Conti Temic microelectronic GmbH
    Inventors: Markus Friebe, Joerg Schrepfer, Rodrigo Garcia Marques, Johannes Petzold, Georg Arbeiter, Stefan Milz
  • Patent number: 10902284
    Abstract: Disclosed is a system for identifying at least one optimum pre-processing technique for text extraction. A data receiving module receives an input image and an expected text pertaining to the input image. Furthermore, a performance module performs a plurality of pre-processing techniques on the input image in order to extract textual information, present in the input image, by using at least one text extraction technique. Subsequently, a recording module records processing time spent on each pre-processing technique performed on the input image. Further, a comparison module compares the textual information with the expected text. Further to comparing the textual information with the expected text, the ranking module may rank each of the plurality of pre-processing techniques based on a result of comparison between the textual information and the expected text, thereby identifying at least one optimum pre-processing technique for text extraction.
    Type: Grant
    Filed: May 21, 2018
    Date of Patent: January 26, 2021
    Inventors: Banumathi Palanichamy, Ameli Merlin Soundararajan, Selvaraj Thangaraj, Yuvarajan Shanmugasundaram, Siva Sakthivel Sadasivam
  • Patent number: 10902598
    Abstract: Systems and methods for automated segmentation of anatomical structures (e.g., heart). Convolutional neural networks (CNNs) may be employed to autonomously segment parts of an anatomical structure represented by image data, such as 3D MRI data. The CNN utilizes two paths, a contracting path and an expanding path. In at least some implementations, the expanding path includes fewer convolution operations than the contracting path. Systems and methods also autonomously calculate an image intensity threshold that differentiates blood from papillary and trabeculae muscles in the interior of an endocardium contour, and autonomously apply the image intensity threshold to define a contour or mask that describes the boundary of the papillary and trabeculae muscles. Systems and methods also calculate contours or masks delineating the endocardium and epicardium using the trained CNN model, and anatomically localize pathologies or functional characteristics of the myocardial muscle using the calculated contours or masks.
    Type: Grant
    Filed: January 25, 2018
    Date of Patent: January 26, 2021
    Assignee: Arterys Inc.
    Inventors: Daniel Irving Golden, Matthieu Le, Jesse Lieman-Sifry, Hok Kan Lau
  • Patent number: 10896326
    Abstract: A system and method for determining a position of a target. The method includes determining a first direction to the target from a first observing position, estimating a first approximate position of the target based on the first direction and the first observing position, determining a second direction to the target from a second observing position, and estimating a second approximate position of the target based on the second direction and the second observing position. The method further includes determining a first approximate intersection point of (i) a first finite length line between the first observing position and the first approximate position of the target, and (ii) a second finite length line between the second observing position and the second approximate position of the target.
    Type: Grant
    Filed: May 23, 2018
    Date of Patent: January 19, 2021
    Assignee: Raytheon Company
    Inventors: Richard C. Vera, Andrew James Neville
  • Patent number: 10896340
    Abstract: In some examples, a computing device receives an image of an optically active article that includes a set of one or more symbols of a symbol set, wherein at least one symbol of the set of one or more symbols comprises a set of encoding regions that are embedded with the symbol. In response to receiving the image, the computing device may determine that a particular image region of the image represents the at least one symbol. For encoding regions within the at least one symbol, the computing device may determine, based at least in part on the determination that the particular image region of the image represents the at least one symbol, whether the one or more encoding regions are active or inactive. The computing device may perform, based at least in part on whether the one or more encoding regions are active or inactive, one or more operations.
    Type: Grant
    Filed: August 19, 2016
    Date of Patent: January 19, 2021
    Assignee: 3M INNOVATIVE PROPERTIES COMPANY
    Inventors: Justin M. Johnson, James W. Howard, James B. Snyder, Thomas J. Dahlin
  • Patent number: 10888295
    Abstract: A control unit of a console functions as an acquisition unit that acquires a radiographic image and imaging conditions in which the radiographic image has been captured. In addition, the control unit functions as a derivation unit that derives the amount of signal included in the radiographic image on the basis of a primary radiation distribution of the radiographic image derived on the basis of the imaging conditions or on the basis of the imaging conditions and a body thickness distribution of an object in the radiographic image and outputs the ratio of the derived amount of signal to the amount of noise included in the radiographic image as an index value of the amount of radiation emitted in the capture of the radiographic image.
    Type: Grant
    Filed: August 23, 2018
    Date of Patent: January 12, 2021
    Assignee: FUJIFILM CORPORATION
    Inventor: Takahiro Kawamura