Patents Examined by Delomia L Gilliard
  • Patent number: 10930396
    Abstract: A weighting processing unit performs a weighting process for an individual lesion similarity which is a similarity between a target lesion and a case lesion of the same type, using a first weighting coefficient corresponding to the degree of contribution of each type of lesion to the specification of a disease name, to calculate a processed individual lesion similarity corresponding to a first purpose of specifying the disease name. In addition, the weighting processing unit performs the weighting process for the individual lesion similarity, using a second weighting coefficient corresponding to the degree of contribution of each type of lesion to the specification of a severity, to calculate a processed individual lesion similarity corresponding to a second purpose of specifying the severity. A total similarity between a target image and a case image is calculated for each purpose on the basis of the processed individual lesion similarities.
    Type: Grant
    Filed: June 13, 2019
    Date of Patent: February 23, 2021
    Assignee: FUJIFILM Corporation
    Inventor: Shoji Kanada
  • Patent number: 10921966
    Abstract: A digitizing device that digitizes by imaging a solid object generates three-dimensional data of the solid object by overlying second imaged data onto first imaged data on a basis of at least one node disposed inside a partial region in the first imaged data and at least one node included in the second imaged data.
    Type: Grant
    Filed: February 6, 2019
    Date of Patent: February 16, 2021
    Assignee: SHARP KABUSHIKI KAISHA
    Inventor: Tohru Nakanishi
  • Patent number: 10922841
    Abstract: An image processing device to improve measurement accuracy for a measurement point includes a corresponding point adjusting unit that causes a display unit to display a measurement point peripheral image that is an image of an area in a periphery of the measurement point extracted from a reference image and a corresponding point peripheral image that is an image of an area in a periphery of a corresponding point extracted from a corresponding image, the measurement point peripheral image and the corresponding point peripheral image being displayed side by side, to adjust a position of the corresponding point found by a corresponding point searching unit.
    Type: Grant
    Filed: May 30, 2017
    Date of Patent: February 16, 2021
    Assignee: SHARP KABUSHIKI KAISHA
    Inventors: Keisuke Omori, Kei Tokui
  • Patent number: 10922847
    Abstract: An encoding apparatus includes an encoding unit that encodes voxel data representing a solid to be modeled, and among a plurality of prediction sections which predict a value of a voxel of interest based on values of one or more reference voxels around the voxel of interest, determines codes, based on a prediction section which makes a correct prediction about the value of the voxel of interest; a unit that acquires a modeling direction; and a control section that controls the encoding unit based on the modeling direction.
    Type: Grant
    Filed: July 24, 2018
    Date of Patent: February 16, 2021
    Assignee: FUJI XEROX CO., LTD.
    Inventor: Taro Yokose
  • Patent number: 10915740
    Abstract: A facial expression feedback system for providing real-time feedback on how closely a user matches his or her facial expression to a target expression is presented. The facial expression feedback system receives sensor data captured by a set of sensors. The facial expression feedback system evaluates the captured sensor data to generate a set of confidence scores with respect to a target facial expression. The system presents the feedback by modifying a multimedia presentation based on the generated set of confidence scores.
    Type: Grant
    Filed: July 28, 2018
    Date of Patent: February 9, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Aldis Sipolins, Jenna Reinen, Hui Wu, Ravi Tejwani, Marco Cavallo
  • Patent number: 10915743
    Abstract: A computer vision system includes a camera that captures a plurality of image frames in a target field. A user interface is coupled to the camera. The user interface is configured to perform accelerated parallel computations in real-time on the plurality of image frames acquired by the camera. The system monitors at-risk humans.
    Type: Grant
    Filed: June 27, 2019
    Date of Patent: February 9, 2021
    Assignee: RoundhouseOne Inc.
    Inventors: Mark Raymond Miller, Archana Ramachandran, Christopher C. Anderson
  • Patent number: 10915815
    Abstract: An information processing method based on contextual signals and a prefrontal cortex-like network includes: selecting a feature vector extractor based on obtained information to perform feature extraction to obtain an information feature vector; inputting the information feature vector into the prefrontal cortex-like network, and performing dimensional matching between the information feature vector and each contextual signal in an input contextual signal set to obtain contextual feature vectors to constitute a contextual feature vector set; and classifying each feature vector in the contextual feature vector set by a feature vector classifier to obtain classification information of the each feature vector to constitute a classification information set. An information processing system based on contextual signals and a prefrontal cortex-like network includes an acquisition module, a feature extraction module, a dimensional matching module, a classification module and an output module.
    Type: Grant
    Filed: April 19, 2019
    Date of Patent: February 9, 2021
    Assignee: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES
    Inventors: Guanxiong Zeng, Yang Chen, Shan Yu
  • Patent number: 10902057
    Abstract: The present invention can, in relation to a single image file including a plurality of original images, record an image file including editing information that represents original image editing content while maintaining the original images. For doing so, an image processing apparatus that performs editing processing in relation to an image file that includes a plurality of images, comprises an editing unit configured to edit an original image in an image file that includes a plurality of original images and generate editing information for reproducing a post-editing image from the original image, and a recording unit configured to, by adding the editing information generated by the editing unit to the image file, record the editing information in the image file.
    Type: Grant
    Filed: September 11, 2018
    Date of Patent: January 26, 2021
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Keita Kato
  • Patent number: 10896527
    Abstract: A method and device for reconstructing a CT image and a storage medium are disclosed. CT scanning is performed on an object to be inspected to obtain projection data. The projection data is processed using a first convolutional neural network to obtain processed projection data. The first convolutional neural network comprises a plurality of convolutional layers. A back-projection operation is performed on the processed projection data to obtain a reconstructed image.
    Type: Grant
    Filed: July 25, 2018
    Date of Patent: January 19, 2021
    Assignees: Tsinghua University, NUCTECH COMPANY LIMITED
    Inventors: Yuxiang Xing, Li Zhang, Jianmin Li, Zhiqiang Chen, Jianping Gu
  • Patent number: 10885651
    Abstract: The various embodiments described herein include an information processing method performed by a wearable electronic device. The wearable electronic device obtains a first initial media file and a second initial media file for a target area. The first initial media file includes a first image acquired based on a first location of the target area. The second initial media file includes a second image acquired based on a second location of the target area. Based on the initial files, the wearable electronic device determines depth information of each target point in the target area. Next, the wearable electronic device selects a first media file from the first and second initial media files, and calculates a second media file. The wearable electronic device then outputs the first and second media files to, respectively, a first output unit and a second output unit of the wearable electronic device.
    Type: Grant
    Filed: November 27, 2018
    Date of Patent: January 5, 2021
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Zhixiong Yu, Zhaopeng Gu, Yao Wang
  • Patent number: 10878280
    Abstract: A method of indexing and searching for video content is provided. For each frame of a first plurality of frames, a first global feature and a first plurality of local features may be identified. The first plurality of local features may be clustered around a first plurality of cluster centers. The first plurality of local features may be converted into a first plurality of binary signatures. An index that maps the first plurality of cluster centers and the first plurality of binary signatures to the first plurality of frames may be generated. A search request associated with a second video may be received and its direct and indirect features may be identified. The identified features of the second video may be compared against the index and a candidate video may be selected as a result of the search request.
    Type: Grant
    Filed: May 21, 2020
    Date of Patent: December 29, 2020
    Assignee: Webkontrol, Inc.
    Inventors: Pavel Koval, Olga Valigourskaia
  • Patent number: 10878258
    Abstract: A method detects roadworks. The method includes steps of: receiving a position of at least one first road sign that indicates the reduction of the maximum permissible top speed to a first vehicle on the current road section on which the first vehicle is travelling by way of a sensor fitted to the first vehicle; receiving a position of at least one second road sign that lifts the reduction of the maximum permissible top speed of a vehicle on the current road section on which the vehicle is travelling by way of the sensor fitted to the first vehicle; determining a first assumption for the position of roadworks from the first position of the at least one first road sign and the first position of the at least one second road sign; and determining a probable position of the roadworks by comparing the first assumption of the position of the roadworks with at least one second assumption that has been determined by at least one second vehicle.
    Type: Grant
    Filed: August 24, 2018
    Date of Patent: December 29, 2020
    Assignee: Bayerische Motoren Werke Aktiengesellschaft
    Inventors: Andreas Hackeloeer, Christian Breil
  • Patent number: 10872401
    Abstract: A method for merging a three-dimensional analysis data record of a tissue sample of a patient with a three-dimensional image data record of the patient indicating, prior to removal, the removal area of the tissue sample. The method includes registering a three-dimensional intermediate data record of the three-dimensional analysis data record. The registering includes transforming analysis data of the three-dimensional analysis data record into intermediate data, corresponding to image data recorded with a modality with which the three-dimensional image data record has been recorded and including a resolution reduced, to determine the three-dimensional intermediate data record corresponding, in terms of resolution, to the image data record; and registering the three-dimensional intermediate data record with the three-dimensional image data record.
    Type: Grant
    Filed: November 26, 2018
    Date of Patent: December 22, 2020
    Assignee: SIEMENS HEALTHCARE GMBH
    Inventors: Sebastian Schmidt, Philipp Hoelzer
  • Patent number: 10872247
    Abstract: According to one embodiment, an image feature emphasis device, a road surface feature analysis device, an image feature emphasis method, and a road surface feature analysis method which can improve the accuracy of detection of features of a road surface in a road surface image are provided. The image feature emphasis device includes a region acquirer and an image feature emphasis processor. The region acquirer acquires a region of a road surface portion from an image that has been captured. The image feature emphasis processor emphasizes a feature of the acquired region of the road surface portion by changing brightness values in the region of the road surface portion on the basis of a maximum brightness value and a minimum brightness value in the region of the road surface portion.
    Type: Grant
    Filed: October 19, 2018
    Date of Patent: December 22, 2020
    Assignees: Kabushiki Kaisha Toshiba, Toshiba Infrastructure Systems & Solutions Corporation
    Inventors: Yoko Yonekawa, Yuuichi Nakamura, Nobuyuki Kumakura, Masaki Shiratsuki, Takahiko Yamazaki
  • Patent number: 10872432
    Abstract: A disparity estimation device calculates, for each of first pixels of a first image and each of second pixels of a second image, a first census feature amount and a second census feature amount, calculates, for each of the first pixels, a first disparity value of the first pixel with integer accuracy, extracts, for each of the first pixels, reference pixels located in positions corresponding to the first disparity value and a near disparity value close to the first disparity value from the second pixels, calculates sub-pixel evaluation values based on the relationship between the pixel values of the first pixel and the neighboring pixel and the pixel values of each of the reference pixels and the neighboring pixel, and estimates a second disparity value of the first pixel with sub-pixel accuracy by equiangular fitting.
    Type: Grant
    Filed: December 28, 2018
    Date of Patent: December 22, 2020
    Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
    Inventors: Takeo Azuma, Kunio Nobori, Satoshi Sato, Nobuhiko Wakai
  • Patent number: 10872230
    Abstract: Methods and systems may provide for facial recognition of at least one input image utilizing hierarchical feature learning and pair-wise classification. Receptive field theory may be used on the input image to generate a pre-processed multi-channel image. Channels in the pre-processed image may be activated based on the amount of feature rich details within the channels. Similarly, local patches may be activated based on the discriminant features within the local patches. Features may be extracted from the local patches and the most discriminant features may be selected in order to perform feature matching on pair sets. The system may utilize patch feature pooling, pair-wise matching, and large-scale training in order to quickly and accurately perform facial recognition at a low cost for both system memory and computation.
    Type: Grant
    Filed: March 27, 2015
    Date of Patent: December 22, 2020
    Assignee: Intel Corporation
    Inventors: Jianguo Li, Yurong Chen, Ke Chen, Yi-Jen Chiu
  • Patent number: 10860840
    Abstract: A computing device stores an acquired image as a transient image template when there is a failure in an image-based authentication of the acquired image and the user of the computing device has provided user credentials that authorize the user to access the computing device. The transient image template may be used to further authorize the user to access the computing device during a predetermined time period. At the expiration of the predetermined time period, the computing device deletes the transient image template. The computing device then reverts to using a baseline image template for performing image-based authentication of the user. The transient image template may also be associated with a location such that the computing device uses the transient image template for image-based authentication when the computing device is at or near the location.
    Type: Grant
    Filed: November 14, 2018
    Date of Patent: December 8, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Amer A. Hassan, Edward C. Giaimo, III
  • Patent number: 10861145
    Abstract: A defect class that can identify true information or false information regarding a defect of an inspection target is received, it is determined whether or not the number of true information and the number of false information are insufficient to set a defect extraction parameter of a predetermined region, a feature amount of the defect is extracted in a region other than the predetermined region when it is determined that the number of true information and the number of false information are insufficient, the feature amounts are totalized by adding the feature amount of the defect extracted in a region other than the predetermined region to the feature amount of the defect extracted in the predetermined region, and the totalized feature amount of the defect is displayed for adjustment of the defect extraction parameters.
    Type: Grant
    Filed: September 27, 2016
    Date of Patent: December 8, 2020
    Assignee: HITACHI HIGH-TECH CORPORATION
    Inventors: Toshifumi Honda, Takahiro Urano, Hisashi Hatano, Hironori Sakurai
  • Patent number: 10853946
    Abstract: Physical object boundary detection techniques and systems are described. In one example, an augmented reality module generates three dimensional point cloud data. This data describes depths at respective points within a physical environment that includes the physical object. A physical object boundary detection module is then employed to filter the point cloud data by removing points that correspond to a ground plane. The module then performs a nearest neighbor search to locate a subset of the points within the filtered point cloud data that correspond to the physical object. Based on this subset, the module projects the subset of points onto the ground plane to generate a two-dimensional boundary. The two-dimensional boundary is then extruded based on a height determined from a point having a maximum distance from the ground plane from the filtered cloud point data.
    Type: Grant
    Filed: May 18, 2018
    Date of Patent: December 1, 2020
    Assignee: eBay Inc.
    Inventors: Patrick Ryan Nelson, Jinrong Xie, Randall Chall Fry
  • Patent number: 10846849
    Abstract: The present invention provides a method and an apparatus for analyzing a cell state, cell death in particular, in an interior of a spheroid non-invasively and quantitatively when the spheroid is cultured. More specifically, the present invention provides a method and an apparatus for analyzing a cell state by implementing optical imaging of a spheroid by using an optical instrument characterized by a high resolution and analyzing the internal structure of the spheroid.
    Type: Grant
    Filed: June 16, 2016
    Date of Patent: November 24, 2020
    Assignee: Hitachi High-Tech Corporation
    Inventors: Naoko Senda, Toshinari Sakurai