Patents Examined by Carol Wang
  • Patent number: 10892050
    Abstract: Methods, systems, and storage components for utilizing a deep neural network(s) for classifying at least one medical image. A deep neural network (DNN) can be configured by an image processing component to contain at least one revived neuron, where the revived neuron has an adjusted value based on a focus-learning function that is transferred to the DNN by the image processing component, where the focus-learning function provides the adjustment by updating the DNN with data that contains a corrected classification with respect to at least one normal image sample derived from a medical image, and where the correction is based on the focus-learning function comparing an annotation associated with an abnormal image sample derived from the medical image to another annotation associated with the at least one normal image.
    Type: Grant
    Filed: April 13, 2018
    Date of Patent: January 12, 2021
    Assignee: International Business Machines Corporation
    Inventors: Xin Zhang, Guo Tong Xie, Xiaolu Zhang, Xiu Li Li, Peng Gao
  • Patent number: 10885622
    Abstract: A system and method for using images from a commodity camera for object scanning, reverse engineering, metrology, assembly, and analysis are disclosed. A particular embodiment includes a mobile imaging system to: enable a user to align an object to be analyzed on a turntable with a stencil; issue commands, by use of a data processor, to the turntable for automatic rotation of the turntable and the object thereon to a particular orientation for a camera of a mobile imaging device; capture a plurality of images of the object being analyzed at different automatic rotations of the turntable; upload the plurality of images of the object to a server via a network interface and a data network; and cause the server to generate a three dimensional (3D) model of the object from the plurality of images of the object.
    Type: Grant
    Filed: June 29, 2018
    Date of Patent: January 5, 2021
    Assignee: Photogauge, Inc.
    Inventors: Sankara J. Subramanian, Azhar H. Khan, Sameer Sharma, Arunachalam Muthukaruppan
  • Patent number: 10878223
    Abstract: Embodiments disclosed herein generally related to a method and system for customizing a customer experience. In one embodiment, a method is provided herein. A computing system receives from a computing device positioned in a facility one or more video streams. The one or more video streams capture a customer in the facility. The computing system identifying an identity of the customer by parsing the one or more video streams to identify one or more audio or visual cues of the customer. The computing system determines, based on the identity of the customer, that the customer has one or more previous transactions at the facility. The computing system predicts, based on the one or more previous transactions, a new transaction at the facility. The computing system notifies the computing device positioned in the facility in preparation of the new transaction.
    Type: Grant
    Filed: November 11, 2019
    Date of Patent: December 29, 2020
    Assignee: Capital One Services, LLC
    Inventors: Michael Mossoba, Gaurang J. Bhatt
  • Patent number: 10877143
    Abstract: A method and device for geo-referencing of supplied aerial image data, which has been recorded by an imaging system and in which a part of the earth's surface is imaged, wherein the geo-referencing of the aerial image data is carried out based on the supplied geo-referenced synthetic aperture radar (SAR) image data, in which the same part of the earth's surface is imaged, wherein the method and system include: determination of essentially point-like radar signatures RS in the geo-referenced SAR image data, provision of a position of the sun for recording time of the aerial image data and the part of the earth's surface imaged therein, determination of elongated cast shadows SS produced in a direction of solar radiation in the aerial image data based on the position of the sun at the time of recording, determination in the aerial image data of initial points AP facing the sun of the determined cast shadows SS, determination of spatially corresponding point-like radar signatures RS and the initial points AP of
    Type: Grant
    Filed: November 29, 2017
    Date of Patent: December 29, 2020
    Assignee: Deutsches Zentrum für Luft- und Raumfahrt e. V.
    Inventors: Hartmut Runge, Thomas Krauss
  • Patent number: 10872270
    Abstract: The present invention relates to an exploit kit detection system based on a neural network using an image and provides a configuration including: a file collection module for collecting a web file created in a web document code and a script code; a distribution module for distributing and storing the collected web file; a management module for assigning, when the web file is received, a job ID to the web file and registering the web file in an inspection target list; an image conversion module for converting a corresponding web file into grayscale, targeting the web file registered in the inspection target list; a classification model, as a classification model based on the neural network, for receiving an image of grayscale and classifying existence and a type of the exploit kit (EK); and a result processing module for receiving a classification result, creating a result data, and transmitting the result data to the distribution module.
    Type: Grant
    Filed: May 17, 2019
    Date of Patent: December 22, 2020
    Assignee: SGA Solutions Co., Ltd.
    Inventors: Sung Jin Kim, Seung Jae Kim, Su Yeon Yoo, Sung Kyu Kim, Soo Hwan Kim
  • Patent number: 10861159
    Abstract: There is provided a method for automatically altering a digital video stream including multiple video input frames, to automatically obtain output frames with a target composition, in which frame metadata relating to objects in one or more of the video input frames is analyzed on a frame-by-frame basis and used by a processor to automatically alter one or more output frames to be more similar to, or to match, the target composition, wherein cropping is performed in 3D. A related system and a related computer program product are also provided.
    Type: Grant
    Filed: July 26, 2017
    Date of Patent: December 8, 2020
    Assignee: Apical Limited
    Inventors: Ilya Romanenko, Vladislav Terekhov
  • Patent number: 10846892
    Abstract: An apparatus includes: an acquisition unit configured to acquire pieces of three-dimensional data of a subject eye obtained at different times, the three-dimensional data including pieces of two-dimensional data obtained at different positions; a first planar alignment unit configured to perform first planar alignment including alignment between the pieces of three-dimensional data in a plane orthogonal to a depth direction of the subject eye; a first depth alignment unit configured to perform first depth alignment including alignment between pieces of two-dimensional data in at least one piece of three-dimensional data among the pieces of three-dimensional data and further including alignment between the pieces of three-dimensional data in the depth direction; and a generation unit configured to generate interpolation data of at least one piece of three-dimensional data among the pieces of three-dimensional data by using a result of the first planar alignment and a result of the first depth alignment.
    Type: Grant
    Filed: September 4, 2018
    Date of Patent: November 24, 2020
    Inventors: Yoshihiko Iwase, Hiroki Uchida
  • Patent number: 10839248
    Abstract: A polarized image acquisition unit 20 acquires polarized images in a plurality of polarization directions. A reflection information generation unit 30 generates reflection information indicating reflection components from the polarized images in the plurality of polarization directions acquired by the polarized image acquisition unit 20. A reflection information using unit 40 uses the reflection information generated by the reflection information generation unit 30 to acquire an image of a viewed object appearing in the polarized images. A depth estimation unit estimates a depth value of a reflective surface area and acquires a position of the viewed object on the basis of an image of the viewed object appearing in the reflective surface area and the estimated depth value. Therefore, the viewed object positioned in, for example, an area of a blind spot can be easily checked.
    Type: Grant
    Filed: August 30, 2016
    Date of Patent: November 17, 2020
    Assignee: Sony Corporation
    Inventors: Yuhi Kondo, Yasutaka Hirasawa, Hideki Oyaizu, Taketo Akama, Suguru Aoki
  • Patent number: 10839228
    Abstract: A method and system for tracking objects in a defined area compares image data of a detected object to profiles of persons that have entered the defined area to find the best match and connect the profile of the best match to the detected object. Identification profiles of persons that have been identified, by presenting their credentials, when entering the defined area are registered as candidates and are later matched with objects detected in the defined area. The system and method use the physical access control system of the defined area to reduce the number of candidates for the detected objects to the most likely candidates. The processing time and need for resources of the object tracking in the defined area are thereby reduced.
    Type: Grant
    Filed: October 18, 2017
    Date of Patent: November 17, 2020
    Assignee: Axis AB
    Inventors: Niclas Danielsson, Anders Hansson
  • Patent number: 10824872
    Abstract: A method for identifying events in a scene captured by a motion video camera comprises two identification processes, a temporary identification process and a long-term identification process. The temporary process includes: analyzing pixel data from captured image frames and identifying events; registering camera processing data relating to each image frame subjected to the identification of events; and adjusting weights belonging to an event identifying operation, wherein the weights are adjusted for achieving high correlation between the result from the event identifying operation and the result from the identification based on analysis of pixels from captured image frames of the captured scene. The long-term identification process includes: identifying events in the captured scene by inputting registered camera processing data to the event identifying operation.
    Type: Grant
    Filed: December 21, 2017
    Date of Patent: November 3, 2020
    Assignee: AXIS AB
    Inventors: Viktor Edpalm, Erik Andersson, Song Yuan
  • Patent number: 10817748
    Abstract: Embodiments of the present disclosure disclose a method and apparatus for outputting information. A specific embodiment of the method comprises: importing a first obstacle point cloud and a second obstacle point cloud having a to-be-calculated similarity into a pre-trained similarity calculation model to generate a similarity between the first obstacle point cloud and the second obstacle point cloud, the similarity calculation model being used for characterizing a corresponding relationship between the two obstacle point clouds and the similarity; and finally outputting the generated similarity. The embodiments have effectively reduced labor and time cost as result of determining various parameters for calculating the similarity.
    Type: Grant
    Filed: July 30, 2018
    Date of Patent: October 27, 2020
    Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Ye Zhang, Jun Wang, Liang Wang
  • Patent number: 10810792
    Abstract: A method for inferring a location of a three-dimensional (3D) object, the method includes receiving sensor data from a plurality of sensors of an autonomous vehicle. The method also includes mapping features extracted from the sensor data to a first data structure corresponding to a feature space of a 3D representation of a spatial area. The method further includes classifying the merged features to identify an object within a vicinity of the autonomous vehicle and projecting a 3D representation of the identified object to a location of the 3D feature space. The method still further includes controlling an action of the autonomous vehicle based on the projected 3D representation.
    Type: Grant
    Filed: May 31, 2018
    Date of Patent: October 20, 2020
    Inventors: Wadim Kehl, German Ros Sanchez
  • Patent number: 10811135
    Abstract: Apparatus, systems, and methods to improve automated identification, monitoring, processing, and control of a condition impacting a patient using image data and artificial intelligence classification are disclosed. An example image processing apparatus includes an artificial intelligence classifier to: process first image data for a patient from a first time to determine a first classification result indicating a first severity of a condition for the patient; and process second image data for the patient from a second time to determine a second classification result indicating a second severity of the condition for the patient. The example image processing apparatus includes a comparator to compare the first classification result and the second classification result to determine a change and a progression of the condition associated with the change. The example image processing apparatus includes an output generator to trigger an action when the progression corresponds to a worsening of the condition.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: October 20, 2020
    Assignee: General Electric Company
    Inventors: Katelyn Nye, Gireesha Rao, Gopal Avinash, Christopher Austin
  • Patent number: 10803606
    Abstract: A temporally consistent belief propagation system includes a disparity map buffer that provides a disparity map of a previous time; a belief propagation unit that generates an energy function according to a first image of a present time, a second image of the present time, a first image of the previous time and the disparity map of the previous time; and a disparity generating unit that generates a disparity map of the present time according to the energy function.
    Type: Grant
    Filed: July 19, 2018
    Date of Patent: October 13, 2020
    Assignees: National Taiwan University, Himax Technologies Limited
    Inventors: Hsin-Yu Hou, Sih-Sian Wu, Da-Fang Chang, Liang-Gee Chen
  • Patent number: 10786225
    Abstract: Disclosed herein is a system and method for characterizing adventitial tissue. In one aspect, a system and method are disclosed that characterizes tissue types within the adventitial tissue including nerve bundles and blood vessels. In a further aspect, the adventitia is imaged and characterized to provide guidance for crossing lesions within an occluded vessel.
    Type: Grant
    Filed: February 26, 2019
    Date of Patent: September 29, 2020
    Inventor: Anuja Nair
  • Patent number: 10789730
    Abstract: A method for determining the position of an object includes: using a projector to project a marker pattern to a projection zone such that a first marker feature of the marker pattern is projected on a first surface portion, using a camera to capture an image of a viewing zone which at least partly overlaps the projection zone, and determining the position of said first surface portion by analyzing the captured image, wherein the viewing zone surrounds the camera, and the image of the viewing zone is captured by forming an annular image of the viewing zone on an image sensor.
    Type: Grant
    Filed: March 16, 2017
    Date of Patent: September 29, 2020
    Assignee: Teknologian Tutkimuskeskus VTT Oy
    Inventor: Vesa Pentikäinen
  • Patent number: 10789677
    Abstract: An image stitching processing method includes: obtaining a first image taken by a first camera module, wherein the first camera module has a first distance from a reference plane; obtaining a second image taken by a second camera module, wherein the second camera module has a second distance from the reference plane; scaling the second image according to a predetermined ratio and stitching the scaled second image with the first image to obtain a third image, wherein the third image has a stitching line between the first image and the scaled second image; determining whether an object image corresponding to an object in the third image is close to or located on the stitching line; identifying the object image to generate an identification confidence value; covering a standard object image on the object image to generate a modified third image; and outputting and displaying the modified third image.
    Type: Grant
    Filed: February 28, 2019
    Date of Patent: September 29, 2020
    Assignee: WISTRON CORP.
    Inventor: Chang-Hsin Lai
  • Patent number: 10776423
    Abstract: Video processing for motor task analysis is described. In various examples, a video of a person carrying out a motor task, such as placing the forefinger on the nose, is input to a trained machine learning system to classify the motor task into one of a plurality of classes. In an example, motion descriptors such as optical flow are computed from pairs of frames of the video and the motion descriptors are input to the machine learning system. The motor task analysis may be used to assess or evaluate neurological conditions such as multiple sclerosis and/or Parkinson's.
    Type: Grant
    Filed: September 3, 2015
    Date of Patent: September 15, 2020
    Assignee: Novartis AG
    Inventors: Peter Kontschieder, Jonas Dorn, Darko Zikic, Antonio Criminsi, Frank Kurt Dahlke
  • Patent number: 10769408
    Abstract: Method and system for automatic chromosome classification is disclosed. The system, alternatively referred as a Residual Convolutional Recurrent Attention Neural Network (Res-CRANN), utilizes property of band sequence of chromosome bands for chromosome classification. The Res-CRANN is end-to-end trainable system, in which a sequence of feature vectors are extracted from the feature maps produced by convolutional layers of a Residual neural networks (ResNet), wherein the feature vectors correspond to visual features representing chromosome bands in an chromosome image. The sequence feature vectors are fed into Recurrent Neural Networks (RNN) augmented with an attention mechanism. The RNN learns the sequence of feature vectors and the attention module concentrates on a plurality of Regions-of-interest (ROIs) of the sequence of feature vectors, wherein the ROIs are specific to a class label of chromosomes.
    Type: Grant
    Filed: January 11, 2019
    Date of Patent: September 8, 2020
    Inventors: Monika Sharma, Swati Jindal, Lovekesh Vig
  • Patent number: 10762639
    Abstract: Current embodiments provided herein include methods for visualizing repetitive movements which use video image files acquired with an appropriate frame rate, which is based on the period of repetition and minimal exposure, to reorganize the presentation of the frames to freeze the motion of the object in motion at any point in the cycle of repetition or to display the isolated frequency of repetition or a video of the amplified motion to enable the detailed visual inspection of an object in motion, and without having to stop the motion.
    Type: Grant
    Filed: January 21, 2020
    Date of Patent: September 1, 2020
    Inventors: Jeffrey R. Hay, Mark William Slemp, Kenneth Ralph Piety