Patents Examined by Xiao Liu
  • Patent number: 12380721
    Abstract: A handwriting recognition method and apparatus, and an electronic device and a storage medium are provided. The method includes: acquiring a text image containing handwritten text; inputting the text image into a convolutional neural network, and extracting a CNN feature and a HOG feature of the text image; and extracting the handwritten text in text image according to the CNN feature and the HOG feature.
    Type: Grant
    Filed: May 27, 2020
    Date of Patent: August 5, 2025
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventor: Huanhuan Zhang
  • Patent number: 12380720
    Abstract: A neural network-based optical character recognition (OCR) method, system, and apparatus may use context provided by a neural network-based language model (LM) to improve character recognition in images. In embodiments, a fuzzy OCR system receives an input image and uses aggregated classes of visually similar characters to identify a most probable aggregated class of visually similar characters. That aggregated class is used as an input to the LM, which, in embodiments, employs a portion of text, for example a word, a phrase, a sentence, or a paragraph, from the input image to provide sufficient context to identify the correct character from the aggregated class of visually similar characters.
    Type: Grant
    Filed: December 30, 2022
    Date of Patent: August 5, 2025
    Assignee: KONICA MINOLTA BUSINESS SOLUTIONS U.S.A., INC.
    Inventor: Ting Xu
  • Patent number: 12361720
    Abstract: A synchronization device is for a vehicle equipped with a plurality of sensors including an image sensor. The synchronization device acquires, as data related to a motion state of the vehicle, first time-series data based on detection data detected by the image sensor and second time-series data based on detection data detected by a sensor other than the image sensor. The synchronization device calculates shift time required for matching the first time-series data with the second time-series data.
    Type: Grant
    Filed: April 26, 2022
    Date of Patent: July 15, 2025
    Assignee: DENSO CORPORATION
    Inventor: Tadayuki Yokota
  • Patent number: 12347220
    Abstract: A handwriting text recognition system based on neural network includes a stroke input processor for receiving tracks of online handwriting texts, a string database for storing a large amount of the tracks; a word recognition neural network; and an after-processor being connected to the string database and the output interface of the text recognition neural network; The handwriting text recognition system based on neural network provides higher rates of confidences. Some natural languages frequently used all over the world can be recognized with a higher accuracy (including languages written from right to left and from left to right). The association relations between the input strokes and the character strings can be provided. It could support any strokes with irregular written orders.
    Type: Grant
    Filed: September 14, 2022
    Date of Patent: July 1, 2025
    Assignee: SUNIAPTE. LTD
    Inventors: Jianming Zhuang, Chung Kwong Chan
  • Patent number: 12333839
    Abstract: A system to classify image of a document using neural network architecture is provided. The system includes a storage device storing the image derived from the document having text information. The system includes a document importer operable to perform optical character recognition to convert image data in the image to machine readable data. The system includes a neural network that perform semantic enrichment and positional context for the terms of interest present in the image. The neural network is configured to take as input the machine-readable data and the image and combine both the machine-readable data and the image to classify the image of the document based on the positional context of the terms of interest.
    Type: Grant
    Filed: August 2, 2022
    Date of Patent: June 17, 2025
    Assignee: UST Global (Singapore) Pte. Limited
    Inventors: Dasaprakash Krishnamurthy, José Pablo Romero Valle, Álvaro Hernández Hernández
  • Patent number: 12333730
    Abstract: A method includes obtaining, from an image sensor, image data of a real-world scene; obtaining, from a depth sensor, sparse depth data of the real-world scene; and passing the image data to a first neural network to obtain one or more object regions of interest (ROIs) and one or more feature map ROIs. Each object ROI includes at least one detected object. The method also includes passing the image data and sparse depth data to a second neural network to obtain one or more dense depth map ROIs; aligning the one or more object ROIs, one or more feature map ROIs, and one or more dense depth map ROIs; and passing the aligned ROIs to a fully convolutional network to obtain a segmentation of the real-world scene. The segmentation contains one or more pixelwise predictions of one or more objects in the real-world scene.
    Type: Grant
    Filed: June 7, 2022
    Date of Patent: June 17, 2025
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Yingen Xiong, Christopher A. Peri
  • Patent number: 12333820
    Abstract: A computer-implemented method and device for mapping a vehicle environment of a vehicle are disclosed. The method comprises determining an occupancy grid representing the vehicle environment, including occupancy probability information of a first set of object detections. The occupancy probability information is determined from first positioning information obtained from a first sensor system. Semantic information and second positioning information associated with the semantic information from one or more semantic information sources is obtained. The semantic information comprises object classification information of a second set of object detections and the second positioning system indicates one or more positions of the second set of object detections with respect to the vehicle. The object classification information of the second set of object detections is combined with the occupancy probability information of the occupancy grid to generate a classified occupancy grid.
    Type: Grant
    Filed: March 29, 2022
    Date of Patent: June 17, 2025
    Assignee: Aptiv Technologies AG
    Inventors: Krzysztof Kogut, Jakub Porebski, Maciej Rózewicz
  • Patent number: 12333430
    Abstract: A method, apparatus, and program product utilize a super resolution machine learning model to reconstruct high resolution seismic data from low resolution seismic data in connection with generating seismic visualizations, e.g., to reduce storage and/or communication costs associated with generating seismic visualizations.
    Type: Grant
    Filed: February 12, 2020
    Date of Patent: June 17, 2025
    Assignee: SCHLUMBERGER TECHNOLOGY CORPORATION
    Inventors: Suhas Suresha, Emilien Dupont, Joseph Matthew Chalupsky
  • Patent number: 12331630
    Abstract: An image system captures images and automatically identifies objects in an object flow at one or more mechanical mud separation machines. A control signal may be generated to change one or more drilling parameters in response to identifying the objects in an object flow. These parameters may be one of a drill speed, an equivalent circulating density, or a control valve.
    Type: Grant
    Filed: June 17, 2022
    Date of Patent: June 17, 2025
    Inventors: Calvin Stuart Holt, Francois Ruel, Martin E. Oehlbeck
  • Patent number: 12327335
    Abstract: Systems, apparatuses, and methods for implementing gradient adaptive ringing control for image resampling are disclosed. A blending alpha calculation circuit generates a blending alpha value for a set of input pixels based on a normalized gradient calculated for the set of input pixels. The normalized gradient is a low-pass filtered gradient of the set of input pixels divided by a maximum gradient for the set of input pixels. The normalized gradient is passed through a mapping function so as to generate the blending alpha value. The mapping function is pre-tuned based on filter coefficients, video content type, pixel format, and so on. An interpolated pixel is generated for the set of input pixels by blending ringing free and ringing prone interpolation coefficients, or by blending results between ringing free and ringing prone interpolation filters, with the blending weight for each filter based on the blending alpha value.
    Type: Grant
    Filed: December 28, 2021
    Date of Patent: June 10, 2025
    Assignee: ATI Technologies ULC
    Inventors: Vladimir Lachine, Jie Zhou
  • Patent number: 12321870
    Abstract: Various embodiments provide an apparatus, a method, and a computer program product. 1. An apparatus incudes at least one processor; and at least one non-transitory memory includes computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: perform an overfitting operation, at an encoder side, to obtain an overfitted probability model, wherein overfitting comprises one or more training operations applied to a probability model, wherein one or more parameters of the probability model are trained; use the overfitted probability model to provide probability estimates to a lossless codec or a substantially lossless codec for encoding data or a portion of the data; and signal information to a decoder on whether to perform the overfitting operation at the decoder side.
    Type: Grant
    Filed: December 1, 2021
    Date of Patent: June 3, 2025
    Assignee: Nokia Technologies Oy
    Inventors: Nannan Zou, Francesco Cricrì, Honglei Zhang, Hamed Rezazadegan Tavakoli, Jani Lainema, Miska Matias Hannuksela
  • Patent number: 12299865
    Abstract: A method of inspecting a composite assembly that includes a core coated with resin. Inspecting the composite assembly includes accessing an image of a cross section of the core, the image having a dot matrix data structure with a matrix of intensity values and identifying a subset of the intensity values that describe a distribution of the resin on the core. Next, the intensity values of the subset of the intensity values are classified to indicate either uniform or non-uniform distribution of the resin on the core. Either a first comparison determining a ratio of uniform resin or a second comparison determining a ratio of non-uniform resin is performed. Based on the first comparison or the second comparison as performed, a quality of the composite assembly is determined. Finally, an indication of the quality of the composite assembly is output.
    Type: Grant
    Filed: April 6, 2022
    Date of Patent: May 13, 2025
    Assignee: The Boeing Company
    Inventors: Eileen O. Kutscha, Garth T. Irvine, Richard Mark Shead
  • Patent number: 12299929
    Abstract: Implementations generally perform robust multi-view multi-target action recognition using reconstructed 3-dimensional (3D) poses. In some implementations, a method includes obtaining a plurality of videos of a plurality of subjects in an environment, where at least one target subject of the plurality of subjects performs one or more actions in the environment. The method further includes tracking the at least one target subject across at least two cameras. The method further includes reconstructing a 3-dimensional (3D) model of the at least one target subject based on the plurality of videos and the tracking of the at least one target subject. The method further includes recognizing the one or more actions of the at least one target subject based on the reconstructing of the 3D model.
    Type: Grant
    Filed: December 22, 2021
    Date of Patent: May 13, 2025
    Assignees: SONY GROUP CORPORATION, SONY CORPORATION OF AMERICA
    Inventors: Wanxin Xu, Ko-Kai Albert Huang
  • Patent number: 12293593
    Abstract: An object detection method is provided. The method includes: acquiring a scene image of a scene; acquiring a three-dimensional point cloud corresponding to the scene; segmenting the scene image into a plurality of sub-regions; merging the plurality of sub-regions according to the three-dimensional point cloud to generate a plurality of region proposals; and performing object detection on the plurality of region proposals to determine a target object to be detected in the scene image. In addition, an object detection device, a terminal device, and a medium are also provided.
    Type: Grant
    Filed: June 9, 2022
    Date of Patent: May 6, 2025
    Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.
    Inventor: Yi Xu
  • Patent number: 12260565
    Abstract: An image processing-based foreign substance detection method in a wireless charging system and a device performing the method are disclosed. A method for detecting a foreign substance includes an operation of acquiring an image of a charging area of a wireless charging system, an operation of detecting, based on an RGB value of a frame of the image, a foreign substance in the charging area, an operation of discriminating a type of the foreign substance, and an operation of performing power control of the wireless charging system according to the type of the foreign substance.
    Type: Grant
    Filed: March 18, 2022
    Date of Patent: March 25, 2025
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Gwangzeen Ko, Jung Ick Moon, Sang-Won Kim, Seong-Min Kim, In Kui Cho, Woo Jin Byun, Je Hoon Yun
  • Patent number: 12260329
    Abstract: The present technology is directed to identifying neutrophil extracellular traps (NETs) in blood. For example, the present technology provides artificial intelligence systems, architectures, and/or programs that can rapidly and/or automatically identify and/or enumerate NETs in peripheral blood smears, CBC scattergrams, and the like. The artificial intelligence architectures can be integrated into current automated imaging and/or analysis systems (e.g., automated imaging systems for performing cell blood counts (CBC)). The artificial intelligence architectures can also be integrated into another computing device, such as a mobile device.
    Type: Grant
    Filed: July 31, 2020
    Date of Patent: March 25, 2025
    Assignee: MONTEFIORE MEDICAL CENTER
    Inventors: Morayma Reyes Gil, Kenji Ikemura, Mohammad Barouqa, Henny Billett, Margarita Kushnir
  • Patent number: 12260596
    Abstract: A computer implemented method for reducing an amount of memory required to store hyperspectral images of an object include: obtaining tensor data representing a hyperspectral image including a first portion depicting an object and a second portion depicting at least a portion of a surrounding environment where the object is located; identifying a portion of the tensor data representing the hyperspectral image that corresponds to the first portion; providing the identified portion of the tensor data representing the hyperspectral image as an input to a feature extraction model; obtaining one or more matrix structures as output by the feature extraction model based on the feature extraction model processing the identified portion of the tensor data, the one or more matrix structures representing a subset of features extracted from the identified portion of the tensor data; and storing the one or more matrix structures in a memory device.
    Type: Grant
    Filed: February 8, 2022
    Date of Patent: March 25, 2025
    Assignee: Apeel Technology, Inc.
    Inventor: Richard Pattison
  • Patent number: 12243284
    Abstract: This application relates to an image recognition technology in the field of computer vision in the field of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain a candidate output feature map of M channels, where M is a positive integer; performing matrix transformation on the M channels of the candidate output feature map based on N matrices, to obtain an output feature map of N channels, where a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.
    Type: Grant
    Filed: January 28, 2022
    Date of Patent: March 4, 2025
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Kai Han, Yunhe Wang, Han Shu, Chunjing Xu
  • Patent number: 12243241
    Abstract: A method for tracking and/or characterizing multiple objects in a sequence of images. The method includes: assigning a neural network to each object to be tracked; providing a memory that is shared by all neural networks; providing a local memory for each neural network, respectively; supplying images from the sequence, and/or details of these images, to each neural network; during the processing of each image and/or image detail by one of the neural networks, generating an address vector from at least one processing product of this neural network; based on this address vector, writing at least one further processing product of the neural network into the shared memory and/or into the local memory, and/or reading out data from this shared memory and/or local memory and further processing the data by the neural network.
    Type: Grant
    Filed: March 16, 2022
    Date of Patent: March 4, 2025
    Assignee: ROBERT BOSCH GMBH
    Inventor: Cosmin Ionut Bercea
  • Patent number: 12236640
    Abstract: Systems and methods for image dense field based view calibration are provided. In one embodiment, an input image is applied to a dense field machine learning model that generates a vertical vector dense field (VVF) and a latitude dense field (LDF) from the input image. The VVF comprises a vertical vector of a projected vanishing point direction for each of the pixels of the input image. The latitude dense field (LDF) comprises a projected latitude value for the pixels of the input image. A dense field map for the input image comprising the VVF and the LDF can be directly or indirectly used for a variety of image processing manipulations. The VVF and LDF can be optionally used to derive traditional camera calibration parameters from uncontrolled images that have undergone undocumented or unknown manipulations.
    Type: Grant
    Filed: March 28, 2022
    Date of Patent: February 25, 2025
    Assignee: Adobe Inc.
    Inventors: Jianming Zhang, Linyi Jin, Kevin Matzen, Oliver Wang, Yannick Hold-Geoffroy