Patents Examined by Jonathan S Lee
  • Patent number: 12784204
    Abstract: An information processing apparatus includes a processor, in which the processor acquires a medical image showing an organ of a subject and disease-related data of the subject, subdivides the medical image into a plurality of patch images, uses a prediction model including a feature amount extraction unit that extracts a feature amount from the patch images and the disease-related data and a correlation information extraction unit that extracts at least correlation information between the plurality of patch images and correlation information between the plurality of patch images and the disease-related data, and inputs the patch images and the disease-related data to the prediction model and outputs a prediction result regarding a disease from the prediction model.
    Type: Grant
    Filed: May 24, 2024
    Date of Patent: November 3, 2026
    Assignee: FUJIFILM CORPORATION
    Inventor: Caihua Wang
  • Patent number: 12784162
    Abstract: A method of predicting an objective quality score of an image or a video includes obtaining at least one selection feature associated with the image or video, and selecting, based on the at least one selection feature, a set of parameters among a plurality of sets of parameters of a learning based prediction model (LBPM). The selected set of parameters results from training the LBPM using training images or videos having the at least one selection feature. The method further includes determining the objective quality score of the image or video by applying the LBPM configured with the selected set of parameters, based on at least one qualifying feature associated with the image or video.
    Type: Grant
    Filed: September 28, 2023
    Date of Patent: November 3, 2026
    Assignee: TENCENT EUROPE (FRANCE) SAS
    Inventor: Joël Jung
  • Patent number: 12784471
    Abstract: A passenger gesture recognition system for gesture recognition of a passenger of a vehicle is carried out using a gesture of the passenger limited to an area around a seat belt. The system includes a controller having target area detection unit that detects a detection target area based on an image captured by an image sensor in an area around webbing of the seat belt fastened to a passenger, a hidden area detection unit that detects an area hidden within the detection target area by the gesture of the passenger, and a signal output unit that outputs an output signal designated for the hidden area and controls a function with respect to the output signal to be performed.
    Type: Grant
    Filed: March 18, 2024
    Date of Patent: November 3, 2026
    Assignees: Hyundai Motor Company, Kia Corporation
    Inventor: Young Rok Kim
  • Patent number: 12776070
    Abstract: The present disclosure provides methods and apparatuses for performing image synthesis. An exemplary image synthesis method includes: acquiring a first image and a second image an image quality of the first image being higher than an image quality of the second image; obtaining a compressed image by compressing the first image; and synthesizing at least a part of the compressed image with at least a part of the second image.
    Type: Grant
    Filed: October 7, 2023
    Date of Patent: October 27, 2026
    Assignee: SIM IP 5 LLC
    Inventors: Binzhe Li, Zhao Wang, Yan Ye, Shiqi Wang
  • Patent number: 12776012
    Abstract: A method for image processing may be provided. The method may include obtaining imaging data of an original image and a correction coefficient matrix of the array dimension. The imaging data may have elements arranged in an array of an array dimension. The imaging data may include an artifact caused by inter-element crosstalk. The correction coefficient matrix may be of the array dimension and is determined based on a trained artifact correction model. The method may also include determining processed image data based on the correction coefficient matrix and the imaging data. The method may further include determining an artifact corrected image of the original image based on the processed image data.
    Type: Grant
    Filed: January 19, 2023
    Date of Patent: October 27, 2026
    Assignee: SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD.
    Inventors: Bin Su, Yanyan Liu
  • Patent number: 12770288
    Abstract: The present invention relates to a method for identifying at least one candidate feature in an image of a scene of interest captured by a camera, and to a method for capturing an image, with spatial variations in image sharpness, of a scene of interest by a camera, and to a method for determining a state xk of a camera at a time tk, as well as to an assembly and two computer program products.
    Type: Grant
    Filed: December 13, 2021
    Date of Patent: October 20, 2026
    Assignee: Verity AG
    Inventors: Markus Hehn, Luciano Beffa
  • Patent number: 12762647
    Abstract: An image acquisition device includes a mask member that includes a mask pixel that changes a transmittance of some parallel waves from a subject on a plane intersecting with an incident direction of the parallel wave, a detector that includes a plurality of pixels that is arranged in a direction intersecting with the incident direction of the parallel wave and detects the parallel wave that has passed through the mask member, and an image processing device that reconstructs an image using compressed sensing based on data regarding a relative moving amount between the mask member and the subject and detection signals of the plurality of pixels input from the detector, in which a size of the mask pixel of the mask member on the plane is smaller than a size of the plurality of pixels along the plane.
    Type: Grant
    Filed: January 10, 2024
    Date of Patent: October 13, 2026
    Assignee: HAMAMATSU PHOTONICS K.K.
    Inventors: Yoshiki Katagiri, Munenori Takumi, Keisuke Uchida, Yuu Takiguchi, Ken-ichi Kitayama, Katsuhiro Ishii, Tomonori Oishi
  • Patent number: 12737870
    Abstract: A method and system for detecting structural performance of fire retardant disc includes the steps of obtaining passage structural information characterizing a structural feature of each passage in a fire retardant disc to be detected, analyzing said passage structural information and measuring a key feature size of each passage, statistically analyzing feature size distribution of each passage according to said key feature size, and determining a structural uniformity state of said fire retardant disc to be detected based on statistical result. The method is able to overcome the disadvantage of manual detection in the structural performance of the fire retardant disc, and effectively detect and assess the structural performance of the fire retardant disc in different use conditions.
    Type: Grant
    Filed: May 16, 2022
    Date of Patent: September 15, 2026
    Assignees: CHINA PETROLEUM & CHEMICAL CORPORATION, SINOPEC RESEARCH INSTITUTE OF SAFETY ENGINEERING CO., LTD.
    Inventors: Lei Bao, Peng Wang, Anfeng Yu, Lili Ding, Wenyi Dang, Guoxin Chen, Meng Gu, Haozhe Wang, Xiaodong Ling
  • Patent number: 12737691
    Abstract: An example method may include receiving, from a mobile device, image information representing an image that includes a depiction of a media of exchange. The method may also include providing the image information as input to a machine learning model implemented by the remote computing device. The method may also include receiving, from the machine learning model, an output comprising a classification and a confidence score, the classification comprising a quantity that corresponds to the media of exchange, the confidence score comprising a probability that the media of exchange in the image corresponds to the quantity. The method may also include comparing the confidence score with respect to one or more evaluation criteria. The method may also include, in response to comparing, providing a user interface for presentation at the mobile device, the user interface comprising an option for establishing a communication channel.
    Type: Grant
    Filed: January 15, 2026
    Date of Patent: September 15, 2026
    Assignee: The Huntington National Bank
    Inventors: Beth Borghese, Alireza Khakpour
  • Patent number: 12737957
    Abstract: Embodiments relate to a method for real-time facial animation, and a processing device for real-time facial animation. The method includes providing a dynamic expression model, receiving tracking data corresponding to a facial expression of a user, estimating tracking parameters based on the dynamic expression model and the tracking data, and refining the dynamic expression model based on the tracking data and estimated tracking parameters. The method may further include generating a graphical representation corresponding to the facial expression of the user based on the tracking parameters. Embodiments pertain to a real-time facial animation system.
    Type: Grant
    Filed: February 29, 2024
    Date of Patent: September 15, 2026
    Assignee: Apple Inc.
    Inventors: Sofien Bouaziz, Mark Pauly
  • Patent number: 12731377
    Abstract: A computing system including one or more processing devices configured to receive a first labeled image set including first images that each include one or more first regions of interest. The one or more processing devices are further configured to receive an unlabeled image set including a plurality of second images, and to identify second regions of interest included in the second images. The one or more processing devices are further configured to compute feature similarity values between the second and first regions of interest, identify a subset of the second regions of interest that have feature similarity values above a predetermined similarity threshold, and apply respective second labels to those second regions of interest. The one or more processing devices are further configured to construct a second labeled image set and train an image classification machine learning model with a training data set that includes the labeled image sets.
    Type: Grant
    Filed: October 4, 2023
    Date of Patent: September 8, 2026
    Assignee: The Boeing Company
    Inventors: Anthony Wayne Baker, Willaredt Hardy
  • Patent number: 12731234
    Abstract: A system and a method for analyzing compressed video. The system comprises a recompression detection engine arranged to analyze a raw video sequence and a compressed video sequence and to determine whether the compressed video has been processed by a predetermined video compression codec for multiple times using a same set of coding parameters.
    Type: Grant
    Filed: January 17, 2023
    Date of Patent: September 8, 2026
    Inventors: Qiang Xu, Hong Yan
  • Patent number: 12711756
    Abstract: Provided are an object detection method and apparatus for an autonomous vehicle. A method of controlling a vehicle includes: detecting a surrounding environment using pieces of data on a driving environment of the vehicle and generating an indication of the surrounding environment; determining, among trained visual prompts received via a network from a server, a target visual prompt corresponding to the pieces of data; generating a merged image by combining a driving image of the autonomous vehicle with the target visual prompt using a predetermined operation; and performing object detection by inputting the merged image into a neural network model of the vehicle, the neural network model configured to infer objects from images inputted thereto.
    Type: Grant
    Filed: May 10, 2024
    Date of Patent: August 18, 2026
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Junho Cho, Moonsub Byeon, Dongwook Lee, Dae Ung Jo
  • Patent number: 12712979
    Abstract: An embodiment of the present disclosure includes: acquiring image data including first image data representing a first image with a plurality of colors including a color other than a special color and second image data representing a second image with the special color; acquiring an amount of representative color material indicating an amount of a plurality of color materials used for printing by a printing device; converting the first image data into first amount-of-color-material data representing a color of the first image by an amount of a plurality of color materials, based on a color conversion profile, and converting the second image data into second amount-of-color-material data representing a color of the second image by an amount of a plurality of color materials, based on the amount of representative color material; and combining the first amount-of-color-material data and the second amount-of-color-material data and thus generating third amount-of-color-material data.
    Type: Grant
    Filed: July 23, 2024
    Date of Patent: August 18, 2026
    Assignee: Seiko Epson Corporation
    Inventor: Hisashi Hirayama
  • Patent number: 12705752
    Abstract: A semantic image segmentation (SIS) system includes: a neural network module trained to generate semantic image segmentation maps based on input images, the semantic image segmentation maps grouping pixels of the input images under respective class labels, respectively; a minimum entropy module configured to, at a first time, determine first minimum entropies of pixels, respectively, in the semantic image segmentation maps generated for a received image and N images received before the received image, where N is an integer greater than or equal to 1; and an adaptation module configured to selectively adjust parameters of the neural network module based on optimization of a loss function that minimizes the first minimum entropies.
    Type: Grant
    Filed: January 16, 2023
    Date of Patent: August 11, 2026
    Assignee: NAVER CORPORATION
    Inventors: Riccardo Volpi, Gabriela Csurka Khedari, Diane Larlus
  • Patent number: 12688719
    Abstract: The disclosed system, apparatus, and method enhance the accuracy of food classification consumption tracking. The method involves obtaining a weight measurement from a scale for a container filled with food. Subsequently, a 2-dimensional (2D) image and a 3-dimensional (3D) point cloud of the container are captured using a 2D camera and a 3D camera, respectively. The method proceeds by scanning the point cloud top-down to detect the shape of the container's rim. Utilizing these extracted features and the rim's shape, the container is accurately identified. A pre-recorded weight of the empty container, specific to the identified container, is then retrieved. Finally, the net weight of the food in the container is calculated by subtracting the weight of the empty container from the total filled weight. The 2D images in combination of the 3D images are also used for identifying the food in the container.
    Type: Grant
    Filed: May 10, 2024
    Date of Patent: July 21, 2026
    Assignee: Foodfx Inc
    Inventors: Fengmin Gong, Jun Du, Samir Virmani, Kianoosh Ghazi
  • Patent number: 12682438
    Abstract: Embodiments herein describe systems and methods for automated clinical image quality assessment and uses thereof are provided. Many embodiments provide instructions and feedback for clinically relevant image quality. Several embodiments provide methods to generate a model to assess image quality.
    Type: Grant
    Filed: October 3, 2022
    Date of Patent: July 14, 2026
    Assignee: The Board of Trustees of the Leland Stanford Junior University
    Inventors: Roxana Daneshjou, Kailas Vodrahalli, James Zou, Justin Ko, Roberto A. Novoa, Albert Chiou
  • Patent number: 12657857
    Abstract: An illumination adjustment apparatus comprises: a recognizer that recognizes an abnormal region in a captured image; and an adjuster that adjusts an intensity of illuminating light in accordance with a shape and a type of the abnormal region.
    Type: Grant
    Filed: April 19, 2022
    Date of Patent: June 16, 2026
    Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
    Inventor: Kiyoshi Hashimoto
  • Patent number: 12657687
    Abstract: A method and an apparatus for generating random images of a herbal formulation includes: a container to hold a herbal formulation, a sweeper tool moveable in multiple degrees of freedom, a controller operatively coupled to the sweeper tool and configured to control the movement of the sweeper tool, a camera positioned to capture an image of the herbal formulation within the container, wherein in use, the sweeper tool is moveable within the container based on one or more randomly generated movement patterns to agitate the herbal formulation within the container, and; wherein the camera is controlled to capture an image of the herbal formulation within the container after the sweeper tool has stopped moving.
    Type: Grant
    Filed: March 15, 2024
    Date of Patent: June 16, 2026
    Assignee: Logistics and Supply Chain MultiTech R&D Centre Limited
    Inventors: Wang Fei Ng, Hiu Yan Yeung, Wing Leung Chow
  • Patent number: 12644699
    Abstract: High-accuracy fitting for complex shapes that can occur in semiconductor processing is performed. A shape model is a curved line that is drawn with one stroke from its start point to its end point along a periphery of a figure that is a combination of one or more ellipses and one or more line segments in an xy-plane defined by an x axis and a y axis which are perpendicular to each other, and constraint conditions of a shape model are derived on the basis of a processing dimension function that represents processing dimensions specified on the basis of singular points in the shape model and that has shape model parameters as its variables, and definition ranges of the processing dimensions.
    Type: Grant
    Filed: July 14, 2021
    Date of Patent: June 2, 2026
    Assignee: Hitachi High-Tech Corporation
    Inventors: Naoto Takano, Hyakka Nakada, Takeshi Ohmori, Yutaka Okuyama