Patents Examined by Jose L. Couso
  • Patent number: 11064902
    Abstract: In accordance with some embodiments, systems, methods, and media for automatically diagnosing IPMNs using multi-modal MRI data are provided. In some embodiments, a system comprises: an MRI scanner; and a processor programmed to: prompt a user to select a slice of T1 and T2 MRI data including the subject's pancreas; generate minimum and maximum intensity projections based consecutive slices of the T1 and T2 MRI data; provide the projections to an image recognition CNN, and receive feature vectors for each from a fully connected layer; perform a canonical correlation analysis to determine correlations between the feature vectors; and provide a resultant vector to an SVM that determines whether the subject's pancreas includes IPMNs based on a vector.
    Type: Grant
    Filed: July 1, 2019
    Date of Patent: July 20, 2021
    Assignees: Mayo Foundation for Medical Education and Research, University of Central Florida Research Foundation, Inc.
    Inventors: Michael B. Wallace, Candice Bolan, Ulas Bagci, Rodney Duane LaLonde, III
  • Patent number: 11062577
    Abstract: Parcel theft deterrence for audio/video (A/V) recording and communication devices, such as video doorbells and security cameras. When an A/V recording and communication device captures image data that includes a parcel, a parcel boundary may be created for monitoring the parcel within. In various embodiments, when the parcel is removed from the parcel boundary, a user alert may be generated to notify a user of a client device associated with the A/V recording and communication device that the parcel has been removed.
    Type: Grant
    Filed: November 11, 2019
    Date of Patent: July 13, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: John Modestine, Elliott Lemberger, James Siminoff, Joshua Roth
  • Patent number: 11064174
    Abstract: The present application provides a white balance processing method and apparatus. The method comprises: recognizing a portrait region in an image; calculating a target white balance gain value according to the area occupied by the portrait region in the image; and performing white balance processing on the image according to the target white balance gain value. The present application resolves the problems of poor user experience due to inaccurate image color restoration caused by a small area proportion of a human face region in an image during white balance adjustment according to the white balance gain value determined according to the area occupied by the human face in the case of a long photography distance.
    Type: Grant
    Filed: July 3, 2018
    Date of Patent: July 13, 2021
    Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.
    Inventor: Quan Yuan
  • Patent number: 11061661
    Abstract: A system and method for enabling graphic-based interoperability between computer executed applications. A computer system operating as a client may display a graphical user interface (GUI) including control graphic items such as buttons, text boxes, etc. A process may examine the graphical image of the GUI to determine if there has been a change over time in the GUI as displayed which updates a control graphic item. If there has been a change over time in the GUI which updates a control graphic item, an action may be taken, for example updating properties of an object construct corresponding to the control graphic item, raising an event corresponding to an object construct corresponding to the control graphic item, or communicating an event to a process.
    Type: Grant
    Filed: December 3, 2019
    Date of Patent: July 13, 2021
    Assignee: NICE LTD.
    Inventors: Alexander Vaindiner, Vitaly Shelest, Yuri Staloverov
  • Patent number: 11049286
    Abstract: Example method includes: transmitting a plurality of probe images from an IoT device at an edge network to a server hosting a target DNN, wherein the plurality of images are injected with a limited amount of noise to probe sensitivities of the target DNN to the red, green, and blue colors; receiving a feedback comprising a plurality of DCT coefficients unique to target DNN from the server hosting the target DNN; computing a plurality of color conversion weights based on the feedback received from the server; converting a set of real-time images from RGB color space to YUV color space using the plurality of color conversion weights unique to the target DNN; compressing the set of real-time images using a quantization table unique to the target DNN by the IoT device; and transmitting the compressed set of real-time images to the server hosting the target DNN for DNN inferences.
    Type: Grant
    Filed: July 31, 2019
    Date of Patent: June 29, 2021
    Assignee: Hewlett Packard Enterprise Development LP
    Inventors: Xiufeng Xie, Kyu-Han Kim
  • Patent number: 11050985
    Abstract: Disclosed in the present invention are an image purple fringe eliminating system, method, a computer-readable storage medium, and a photographing device. The system traverses an image, calculates a hue of a pixel, counts a ratio of purple hue to adjacent purple hue pixels in the image, and calculates a dynamic purple fringe detection threshold; creates a mask with the same size as the image acquired by an image acquisition module, and detects the pixels that fall into a purple fringe area; corrects the detected pixel falling into the purple fringe area, correcting both a red channel intensity value and a blue channel intensity value of the pixels within the purple fringe region using a green channel intensity value. The invention can automatically correct the purple fringe of the image, improve the image shooting quality and the user experience.
    Type: Grant
    Filed: January 11, 2018
    Date of Patent: June 29, 2021
    Assignee: ARASHI VISION INC.
    Inventors: Jinlin Cai, Jingkang Liu
  • Patent number: 11042782
    Abstract: Techniques are provided for training and operation of a topic-guided image captioning system. A methodology implementing the techniques according to an embodiment includes generating image feature vectors, for an image to be captioned, based on application of a convolutional neural network (CNN) to the image. The method further includes generating the caption based on application of a recurrent neural network (RNN) to the image feature vectors. The RNN is configured as a long short-term memory (LSTM) RNN. The method further includes training the LSTM RNN with training images and associated training captions. The training is based on a combination of: feature vectors of the training image; feature vectors of the associated training caption; and a multimodal compact bilinear (MCB) pooling of the training caption feature vectors and an estimated topic of the training image. The estimated topic is generated by an application of the CNN to the training image.
    Type: Grant
    Filed: March 20, 2017
    Date of Patent: June 22, 2021
    Assignee: INTEL CORPORATION
    Inventors: Zhou Su, Jianguo Li, Anbang Yao, Yurong Chen
  • Patent number: 11039805
    Abstract: A method relates to the use of deep learning techniques, which may be implemented using trained neural networks (50), to estimate various types of missing projection or other unreconstructed data. Similarly, the method may also be employed to replace or correct corrupted or erroneous projection data as opposed to estimating missing projection data.
    Type: Grant
    Filed: January 5, 2017
    Date of Patent: June 22, 2021
    Assignee: General Electric Company
    Inventors: Bruno Kristiaan Bernard De Man, Bernhard Erich Hermann Claus, Jiang Hsieh, Yannan Jin, Zhanfeng Xing
  • Patent number: 11042761
    Abstract: Embodiments of a method and system for sensing an obstacle, a computer device, and a computer-readable storage medium are provided. The method can include: capturing continuously, by first and second cameras adjacently arranged on a motor vehicle, obstacles around the motor vehicle, to obtain at least a first obstacle image and a second obstacle image respectively; associating the first obstacle image with the second obstacle image; determining whether the first obstacle image and the second obstacle image comprise the same obstacle. By means of some of the disclosed methods and systems, an obstacle can be real-time sensed by a motor vehicle in a large field of view, such as, a range of 360° around the vehicle.
    Type: Grant
    Filed: July 15, 2019
    Date of Patent: June 22, 2021
    Assignee: Baidu Online Network Technology (Beijing) Co., LTD.
    Inventors: Guo Li, Han Gao, Xun Sun, Tian Xia
  • Patent number: 11030758
    Abstract: An automated tissue section slicing, staining, and imaging system efficiently registers full-resolution tissue section images by applying scaled transformation matrices computed to register downsampled tissue section images to the full-resolution tissue section images.
    Type: Grant
    Filed: May 18, 2019
    Date of Patent: June 8, 2021
    Assignee: Strateos, Inc.
    Inventor: Christopher Rhodes
  • Patent number: 11030474
    Abstract: Implementations disclosed herein more accurately and efficiently identify planar region boundaries corresponding to surfaces in a physical environment based on identifying intersections. In some implementations a detected planar region is altered, e.g., trimmed or extended, based on detecting an intersection of the planar region with an expansion of another planar region. In other implementations, a detected planar region is altered, e.g., trimmed or extended, based on detecting an intersection of the planar region with a detected edge line.
    Type: Grant
    Filed: May 28, 2019
    Date of Patent: June 8, 2021
    Assignee: Apple Inc.
    Inventors: Aitor Aldoma Buchaca, Michael Jaison Gnanasekar, Oliver M. Dunkley
  • Patent number: 11030480
    Abstract: An electronic device and a method for controlling the same include inputting an input image into an artificial intelligence model, acquiring a feature map for the input image, converting the feature map through a lookup table corresponding to the feature map, and storing the converted feature map by compressing the feature map through a compression mode corresponding to the feature map.
    Type: Grant
    Filed: August 30, 2019
    Date of Patent: June 8, 2021
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Insang Cho, Wonjae Lee, Chanyoung Hwang
  • Patent number: 11024053
    Abstract: Methods and systems for performing location and movement determination in a three-dimensional environment using a mobile device with a camera are disclosed. The methods and systems perform the steps of capturing one or more images of a user using the camera on the mobile computing device, determining the user from the images using a machine learning algorithm, determining a pose associated with the user using a machine vision algorithm, determining a depth of the user with respect to the camera based on the pose and an input height of the user using a binary search process, and determining the location of the user in the environment based on the pose and the depth.
    Type: Grant
    Filed: December 17, 2020
    Date of Patent: June 1, 2021
    Assignee: NEX Team Inc.
    Inventors: Qi Zhang, Wing Hung Chan, Keng Fai Lee, Long Mak
  • Patent number: 11014211
    Abstract: A monocular vision six-dimensional measurement method for high-dynamic large-range arbitrary contouring error of a CNC machine tool of the present invention belongs to the field of dynamic error detection of machine tools, and relates to a six-dimensional measurement method for high-dynamic large-range arbitrary contouring error of a CNC machine tool using a monocular vision measurement technology with short-time stroboscopic illumination and a priori standard plate. The method designs a measurement fixture and a measurement system, and uses a monocular vision pose algorithm to improve both the visual measurable dimension and range of interpolated contour in combination with priori knowledge. In light of the principle of error distribution, a small field of view is used to enhance the measurement accuracy of the coded primitives in the images.
    Type: Grant
    Filed: November 7, 2017
    Date of Patent: May 25, 2021
    Assignee: DALIAN UNIVERSITY OF TECHNOLOGY
    Inventors: Wei Liu, Zhenyuan Jia, Xiao Li, Yi Pan, Xin Ma, Jianwei Ma
  • Patent number: 11016006
    Abstract: A real-time imaging method and system for monitoring an assay process performed on a biological sample is described. In some embodiments, the method and system can be used to measure and control a reagent volume confined to a space between a cover and a substrate, which is particularly useful for controlling for evaporation in a thin-film staining environment. In particular embodiments, the disclosed reagent volume sensing and replenishment method and system are resistant to system noises generated during operation, for example, system noise due to vibration, field of view blockage by dispenser systems, differences in reagent colors, and changing tissue colors.
    Type: Grant
    Filed: October 19, 2018
    Date of Patent: May 25, 2021
    Assignee: Ventana Medical Systems, Inc.
    Inventors: Yu-Heng Cheng, Lisa A. Jones, Jessica A. Wifall
  • Patent number: 11010634
    Abstract: An apparatus includes a processor that matches of local-feature-amounts in a state where an image of a measurement target captured by an image-sensor and a projective-transformed image of three-dimensional design data of the measurement target substantially overlap each other on a display to search the captured image and a virtual image generated from the projective-transformed image for a plurality of feature-point pairs with similar local-feature-amounts of an image, estimates a temporary-external-parameter related to a position and orientation of the image-sensor, compares an initial-external-parameter and the temporary-external-parameter to diagnose reliability of the temporary-external-parameter, and selects, among the feature-point pairs, a specified number of feature-point pairs with a score value indicating similarity between two feature-points forming each feature-point pair equal to or higher than a threshold value, estimate a final-external-parameter using the selected feature-point pairs, and disp
    Type: Grant
    Filed: July 8, 2019
    Date of Patent: May 18, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Fumiyuki Takahashi, Tetsuo Koezuka
  • Patent number: 11010898
    Abstract: Processes and techniques are disclosed to identify regions of suspected malignancy and their localization within a body part or organ. These methods rely on the analysis of infrared images to identify thermal abnormalities using image post-processing techniques, numerical modeling, iterative solutions methodology or a digital library. The methods utilize noninvasive, non-radiative and no contact infrared imaging that can be used for breast cancer screening for improved prognosis.
    Type: Grant
    Filed: June 12, 2019
    Date of Patent: May 18, 2021
    Assignee: Bired Imaging, Inc.
    Inventors: Satish G. Kandlikar, Donnette Dabydeen, Lori Medeiros, Pradyumna Phatak, Jose Luis Gonzalez Hernandez, Alyssa Owens
  • Patent number: 11006148
    Abstract: The present invention relates to a method for adding a graphical object to image data of one or more image frames comprising a first image frame, the graphical object being added during encoding of the one or more image frames using an encoder, wherein the image data generator is converting the graphical object into a first set of discrete frequency transform, DFT, blocks each DFT block being associated with a position in the one or more image frames to which the DFT block corresponds. The encoder is performing DFT on a plurality of block of pixels of the first image frame, to output a second set of DFT blocks and then replacing a subset of DFT blocks of the second set of DFT blocks with the first set of DFT blocks according to the positions associated with the first set of DFT blocks.
    Type: Grant
    Filed: November 4, 2019
    Date of Patent: May 11, 2021
    Assignee: AXIS AB
    Inventors: Song Yuan, Viktor Edpalm
  • Patent number: 10997700
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for normalizing skin tone brightness are disclosed. In one aspect, a method includes the actions of receiving a color image that includes a representation of a face. The actions further include selecting a group of pixels in the color image that includes the representation of the face. The actions further include determining a brightness value that represents a brightness of the group of pixels in the color image that includes the representation of the face. The actions further include determining a brightness difference value. The actions further include comparing the brightness difference value to an upper threshold brightness difference value and a lower threshold brightness difference value. The actions further include determining whether to adjust a brightness of the color image that includes the representation of the face.
    Type: Grant
    Filed: December 31, 2018
    Date of Patent: May 4, 2021
    Assignee: Idemia Identity & Security USA LLC
    Inventors: Yecheng Wu, Brian K. Martin
  • Patent number: 10991081
    Abstract: This application discloses a technology for flattening a photographed page of a book and straightening texts therein. The technology uses one or more mathematical models to represent a curved shape of the photographed page with certain parameters. The technology also uses one or more photographic image processing techniques to dewarp the photographed page using the parameters of the curved shape. The technology uses one or more additional parameters that represent certain features of the photographed page to dewarp the photographed page.
    Type: Grant
    Filed: December 31, 2020
    Date of Patent: April 27, 2021
    Assignee: VoyagerX, Inc.
    Inventors: Moogung Kim, Kunwoo Park, Eunsung Han, Sedong Nam