Patents Examined by Matthew C. Bella
  • Patent number: 10342645
    Abstract: A method for optimizing initial discriminating information extracted from a two-dimensional image of the patient dental arches, referred to as “acquired image”, by a three-dimensional digital reference model of at least one portion of a patient arch, the method including the steps: C1. assessing quality of the initial discriminating information and quality threshold, filtering to keep only the initial discriminating information that has quality higher than the quality threshold, and defining “the discriminating information to be tested” as the initial discriminating information selected; C2. testing consistency between the discriminating information to be tested and reference model; C3. assessing test result and, in accordance with the assessment: adding discriminating information that was not kept to the discriminating information to be tested and/or deleting discriminating information from the discriminating information to be tested, and then returning to step C2.
    Type: Grant
    Filed: October 27, 2015
    Date of Patent: July 9, 2019
    Assignee: DENTAL MONITORING
    Inventors: Philippe Salah, William Ayache, Laurent Debraux, Guillaume Ghyselinck, Thomas Pellissard
  • Patent number: 10339649
    Abstract: A computer-implemented method for generating a digital model of an individual intraoral component from a digital model of a patient's dentition obtains a 3-D digital mesh model of the patient's dentition and performs automatic tooth component segmentation operation on the obtained mesh model. Automated segmentation results display. Interactive segmentation of the automated segmentation results is performed according to an operator instruction. Segmentation results are displayed and stored.
    Type: Grant
    Filed: September 11, 2015
    Date of Patent: July 2, 2019
    Assignee: Carestream Dental Technology Topco Limited
    Inventors: Wei Ye, Shoupu Chen, Xavier Ripoche, Delphine Reynard
  • Patent number: 10339650
    Abstract: A system and method is disclosed to reduce variation of the clinical decision making process when an image reporting and data system (IRADS) for medical diagnosis is used. Image reporting and data systems provide guidelines for an operator to identify images as belonging to one of a number of categories and specific clinical actions are then recommended based upon such categories. Some clinical actions such as biopsies may be recommended by IRADS even when they are not necessary. The present inventive concept is configured to utilize a Computer-Assisted Diagnosis (CAD) system that is specifically programmed to minimize discrepancies between the recommended clinical actions of an individual or specific group of experts using the standard IRADS process and the optimum clinical actions based on correlation with biopsy proven data. The resulting CAD system reduces the number of unnecessary clinical actions such as biopsies based on the operator's error profile.
    Type: Grant
    Filed: July 1, 2016
    Date of Patent: July 2, 2019
    Assignee: Koios Medical, Inc.
    Inventors: Christine I. Podilchuk, Ajit Jairaj, Lev Barinov, William Hulbert, Richard Mammone
  • Patent number: 10314558
    Abstract: An image processing apparatus acquires a radiation image captured by irradiating an object with a radiation from a radiation source, estimates a scattered radiation image included in the acquired radiation image, and outputs a corrected image obtained by reducing the scattered radiation image from the acquired radiation image. The image processing apparatus estimates the scattered radiation image by applying a scattered radiation model for obtaining a scattered radiation component to the acquired radiation image based on a specific frequency component of an output of a first function and a specific frequency component of an output of a second function different from the first function.
    Type: Grant
    Filed: February 24, 2016
    Date of Patent: June 11, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Takeshi Noda, Yukari Nakashoji
  • Patent number: 10318010
    Abstract: The technology disclosed relates to automatically (e.g., programmatically) initializing predictive information for tracking a complex control object (e.g., hand, hand and tool combination, robot end effector) based upon information about characteristics of the object determined from sets of collected observed information. Automated initialization techniques obviate the need for special and often bizarre start-up rituals (place your hands on the screen at the places indicated during a full moon, and so forth) required by conventional techniques. In implementations, systems can refine initial predictive information to reflect an observed condition based on comparison of the observed with an analysis of sets of collected observed information.
    Type: Grant
    Filed: February 5, 2018
    Date of Patent: June 11, 2019
    Assignee: Leap Motion, Inc.
    Inventor: Kevin A. Horowitz
  • Patent number: 10319106
    Abstract: A method for processing multiple image sources comprises steps: receiving a plurality of first images from a first device; arranging the first images in an order of times of capturing the first images; receiving at least one second image from at least one second device; arranging together the second image and the most spatially neighboring first images according to first and second positioning information of the first and second images; arranging the first and second images sharing an identical geographic space into an identical geographic group; arranging the first and second images, which have an identical still background, into an identical background group; sorting the first and second images of each background group in an order from a large background to a small background or in a reverse order; and processing the sorted images into a video. The present invention makes viewers watching the video feel smooth without abruptness.
    Type: Grant
    Filed: September 11, 2017
    Date of Patent: June 11, 2019
    Inventor: Chin-Min Liu
  • Patent number: 10311746
    Abstract: The present disclosure relates to systems and methods for monitoring posture of a user of a wearable apparatus. In one implementation, the system may include an image sensor configured to capture one or more images from an environment of the user of the wearable apparatus and at least one processing device. The at least one processing device may be configured to analyze the one or more images to determine at least one indicator of the posture of the user, determine feedback for the user based on the at least one indicator of the posture of the user, and cause the feedback to be output to the user.
    Type: Grant
    Filed: June 14, 2017
    Date of Patent: June 4, 2019
    Assignee: OrCam Technologies Ltd.
    Inventors: Yonatan Wexler, Amnon Shashua
  • Patent number: 10311549
    Abstract: Even in a case where radiation imaging is performed using a grid, data lack which occurs at a time of radiation detection is appropriately corrected. An FPD controller 105 obtains data of an image captured by detecting radial rays. A data lack ratio calculation unit 111 calculates data lack ratios in the image data. A fitting unit 112 performs fitting so that a model function representing the data lack fits the data lack ratios. A correction processing unit 113 corrects the image data in accordance with the model function obtained by the fitting.
    Type: Grant
    Filed: August 1, 2014
    Date of Patent: June 4, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Takeshi Noda
  • Patent number: 10303963
    Abstract: Provided, in an aspect, is a method for improving security in an automated teller machine (ATM) network, which includes prompting a user, via the ATM, to provide a biometric sample; receiving the sample from a biometric device of the ATM; determining that the sample is not blacklisted; and allowing the user to complete a transaction. Because the method includes storing anonymized event details, which include the biometric sample separate from user-identifying information, the method both improves privacy for law-abiding users and deters malicious use by others.
    Type: Grant
    Filed: July 9, 2018
    Date of Patent: May 28, 2019
    Assignee: Capital One Services, LLC
    Inventors: Joshua Edwards, Michael Mossoba, Abdelkader Benkreira
  • Patent number: 10303981
    Abstract: A method for learning parameters of an object detector based on R-CNN is provided. The method includes steps of: a learning device (a) if training image is acquired, instructing (i) convolutional layers to generate feature maps by applying convolution operations to the training image, (ii) an RPN to output ROI regression information and matching information (iii) a proposal layer to output ROI candidates as ROI proposals by referring to the ROI regression information and the matching information, and (iv) a proposal-selecting layer to output the ROI proposals by referring to the training image; (b) instructing pooling layers to generate feature vectors by pooling regions in the feature map, and instructing FC layers to generate object regression information and object class information; and (c) instructing first loss layers to calculate and backpropagate object class loss and object regression loss, to thereby learn parameters of the FC layers and the convolutional layers.
    Type: Grant
    Filed: October 4, 2018
    Date of Patent: May 28, 2019
    Assignee: StradVision, Inc.
    Inventors: Kye-Hyeon Kim, Yongjoong Kim, Insu Kim, Hak-Kyoung Kim, Woonhyun Nam, Sukhoon Boo, Myungchul Sung, Donghun Yeo, Wooju Ryu, Taewoong Jang, Kyungjoong Jeong, Hongmo Je, Hojin Cho
  • Patent number: 10290102
    Abstract: An image registration apparatus (118) includes an image quality driven image registration determiner (202) that determines an image quality driven image registration for a set of images to register based on a non-rigid registration (204), which includes an optimization of an image similarity term and a regularization term, and a registration steering factor, and a registration component (206) that registers the set of images using the image quality driven image registration. A method determining an image quality driven image registration for a set of images to register based on a non-rigid registration, which includes an optimization of an image similarity term and a regularization term, and a registration steering factor, and registering the set of images using the fidelity driven image registration, generating a set of registered images.
    Type: Grant
    Filed: June 18, 2013
    Date of Patent: May 14, 2019
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Cristian Lorenz, Sven Kabus, Tobias Klinder, Jens Von Berg
  • Patent number: 10291255
    Abstract: An arithmetic encoder is provided for converting an event sequence comprised of a plurality of events to an information sequence comprised of at least one information piece, and includes a core engine for receiving an event of the event sequence, and a probability estimate from a probability estimator, and generating zero or more pieces of the information sequence responsive to the received event and the probability estimate by bounding the ratio of events to information pieces. An arithmetic encoder is provided that is capable of constraining a number of events in at least one event sequence as a function of the number of generated information pieces in at least one information sequence.
    Type: Grant
    Filed: April 9, 2018
    Date of Patent: May 14, 2019
    Assignee: NTT DOCOMO, INC.
    Inventor: Frank Jan Bossen
  • Patent number: 10282616
    Abstract: Method and system for finding targets within visual data, comprising receiving target object information. Generating a set of target object semantic attributes from the target object information. Identifying a plurality of candidate objects within visual data. Generating a set of low-level feature descriptors from the visual data for each candidate object. Generating from the set of low-level feature descriptors a set of candidate semantic attributes for each candidate object within the visual data. Identifying one or more portions of the visual data containing a candidate object, from the plurality of candidate objects, having a set of candidate object semantic attributes that match the set of target object semantic attributes. Providing an output indicating the identified one or more portions of the visual data.
    Type: Grant
    Filed: October 17, 2014
    Date of Patent: May 7, 2019
    Assignee: Vision Semantics Limited
    Inventors: Shaogang Sean Gong, Timothy Miguel Hospedales
  • Patent number: 10275669
    Abstract: Advanced driver assistance systems (ADAS) and methods for object detection such as traffic lights, speed signs, in an automotive environment, are disclosed. In an embodiment, ADAS includes camera system for capturing image frames of at least a part of surroundings of vehicle, memory comprising image processing instructions and processing system for detecting one or more objects in a coarse detection followed by a fine detection. Coarse detection includes detecting presence of the one or more objects in non-consecutive image frames of the image frames, where non-consecutive image frames are determined by skipping one or more frames of the image frames. Upon detection of presence of the one or more objects in coarse detection, fine detection of the one or more objects is performed in a predetermined number of neighboring image frames of a frame in which the presence of the objects is detected in coarse detection.
    Type: Grant
    Filed: September 8, 2016
    Date of Patent: April 30, 2019
    Assignee: Lightmetrics Technologies PVT. LTD.
    Inventors: Mithun Uliyar, Gururaj Putraya, Soumik Ukil, Krishna A G, Ravi Shenoy, Pushkar Patwardhan
  • Patent number: 10269133
    Abstract: Embodiments include devices and methods for capturing images of a game by an unmanned autonomous vehicle (UAV). A processor of the UAV may determine game play rules of the game. The processor may determine a location of the game object. The processor may calculate a position from which to capture an image of the game based on the determined game play rules and the location of the game object. The processor may capture an image of the game from the calculated position.
    Type: Grant
    Filed: January 3, 2017
    Date of Patent: April 23, 2019
    Assignee: QUALCOMM Incorporated
    Inventor: Evan Hildreth
  • Patent number: 10265045
    Abstract: A medical diagnostic imaging apparatus according to an embodiment includes control circuitry. The control circuitry obtains three-dimensional medical image data of acquiring an area of an object. The control circuitry defines a setting region on the three-dimensional medical image data. The control circuitry divides the setting region into a region of interest and a region other than that by at least a single boundary position. The control circuitry generates, from the three-dimensional medical image data, an image in which the region of interest and the region other than that are distinguished from each other. The control circuitry calculates information about at least one of a volume of and a motion index of the region of interest. The control circuitry displays the calculated information for the region of interest in the image.
    Type: Grant
    Filed: November 2, 2015
    Date of Patent: April 23, 2019
    Assignee: Toshiba Medical Systems Corporation
    Inventor: Yasuhiko Abe
  • Patent number: 10262216
    Abstract: Computerized methods are performable by a driver assistance system while the host vehicle is moving. The driver assistance system includes a camera connectible to a processor. First and second image frames are captured from the field of view of the camera. Corresponding image points of the road are tracked from the first image frame to the second image frame. Image motion between the corresponding image points of the road is processed to detect a hazard in the road. The corresponding image points are determined to be of a moving shadow cast on the road to avoid a false positive detection of a hazard in the road or the corresponding image points are determined not to be of a moving shadow cast on the road to verify detection of a hazard in the road.
    Type: Grant
    Filed: January 10, 2018
    Date of Patent: April 16, 2019
    Assignee: MOBILEYE VISION TECHNOLOGIES LTD.
    Inventors: Gideon Stein, Erez Dagan
  • Patent number: 10255473
    Abstract: A method and a resistivity image logging tool connected or connectable to one or more processing devices process geological log data to construct missing information from destroyed or occluded parts using cues from observed data. The geological log data signals can be generated through use of the logging tool having one or more electrodes interacting with a formation intersected by a borehole. The processing involves the steps of: in respect of one or more data dimensions associated with missing values in a log data set, decomposing the signal into a plurality of morphological components; and morphologically reconstructing the signal such that missing values are estimated.
    Type: Grant
    Filed: March 28, 2017
    Date of Patent: April 9, 2019
    Assignee: Reeves Wireline Technologies Limited
    Inventors: Peter Adrian Spencer Elkington, Said Assous
  • Patent number: 10255518
    Abstract: An image determining method for scanning an image and determining specific image pixels of a specific image. The method comprises: determining at least one pixel in a first row having brightness value larger than a threshold value as the specific image pixel; defining a leftmost pixel and a rightmost pixel of the specific image pixel in the first row as a leftmost edge and a rightmost edge of a first specific image range; and defining a second specific image range in a second row of the image, which is next to the first row. Column positions of a leftmost edge and a rightmost edge of the second specific image range are respectively the same with column positions of the leftmost edge and the rightmost edge of the first specific image range. Via this method, the determining for the specific image pixels is more accurate.
    Type: Grant
    Filed: July 17, 2016
    Date of Patent: April 9, 2019
    Assignee: PixArt Imaging Inc.
    Inventors: Chia-Cheun Liang, Shu-Sian Yang, Yi-Hsien Ko
  • Patent number: 10248886
    Abstract: At least some of the exemplary embodiments are a method. The method includes obtaining, at an underwater imaging device, a stream of images of geophysical surveying equipment, wherein the geophysical surveying equipment includes a target pattern having a calibrated image size. The geophysical surveying equipment is tracked using the image stream and the target pattern. The method further includes capturing from the image stream, a single image of the images of the geophysical surveying equipment, wherein the single image comprises an image of the target pattern having an apparent size. Based on the calibrated image size and the apparent size, a distance between the underwater imaging device and the geophysical surveying equipment is determined.
    Type: Grant
    Filed: April 30, 2014
    Date of Patent: April 2, 2019
    Assignee: PGS Geophysical AS
    Inventors: Torbjørn Ursin, Michael Malling, Geir Andre Motzfeldt Drange