Patents Examined by Dov Popovici
  • Patent number: 12387085
    Abstract: A deep learning device and system including the same is provided. The deep learning device comprising processing circuitry configured to determine whether a received image is abnormal using an anomaly detection model; merge at least some vectors extracted from the anomaly detection model; input, to a probability approximation model, principal components generated by a principal component analysis (PCA) to detect whether out of distribution (OOD) occurs in data of the received image; store a result of the determinations; and extract at least some the data in which the OOD occurs, as target labeling, using a target labeling extraction model when a rate of the data in which the OOD occurs is greater than or equal to a threshold value, wherein the anomaly detection model determines whether the received image is abnormal using the target labeling.
    Type: Grant
    Filed: November 18, 2021
    Date of Patent: August 12, 2025
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Young Jae Kim, Kae Weon You, Ji Ung Lee, Jun Haeng Lee, Kyoung Hoon Kang, Young Hak Lee
  • Patent number: 12348684
    Abstract: The present invention provides an inspection apparatus that compares a reference image with a printed material that has been printed to perform inspection of the printed material, and a method of controlling the same. The inspection apparatus exclusively controls, as an inspection mode of the inspection, an inspection mode between a mode for switching a discharge destination of a printed material in which a defect is recognized, and an inspection job of inspecting a printed material printed by a print job in which one copy includes a plurality of printed materials or an inspection type of inspecting printed materials having a sequential order.
    Type: Grant
    Filed: March 18, 2022
    Date of Patent: July 1, 2025
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Ryo Kazumi
  • Patent number: 12340621
    Abstract: A method of detecting an object in an image includes (i) processing, with a machine-learned model, pixel intensities of a pixel pair in a first region of the image, to determine a first confidence score representing a likelihood of the object being present within the first region, and (ii) determining, based on the first confidence score, presence of the object in the first region.
    Type: Grant
    Filed: August 5, 2022
    Date of Patent: June 24, 2025
    Assignee: OmniVision Technologies, Inc.
    Inventors: Wenchao Zhang, Guansong Liu
  • Patent number: 12341938
    Abstract: An image processing apparatus equipped with a scanner has a function of transmitting image data generated using the scanner to a folder. The image processing apparatus displays a screen including a display area for displaying information indicating a transmission destination of the image data and an area for receiving an instruction to transmit the image data to the transmission destination. In a case where a folder path specified as the transmission destination and having folder names arranged in order from an upper hierarchy to a target folder does not fit within the display area, the folder path is displayed in the display area in a format in which a beginning part of the folder path is omitted.
    Type: Grant
    Filed: February 13, 2024
    Date of Patent: June 24, 2025
    Assignee: Canon Kabushiki Kaisha
    Inventor: Ken Tokita
  • Patent number: 12332971
    Abstract: Streaming machine telemetry (SMT) event counters are placed in critical code paths of software executing on a storage system. Each monitoring interval the values of the SMT counters are reported. When a critical error occurs on the storage system, a time series set of SMT counters from a set of previous monitoring intervals is labeled with the error type and used as a training example for a learning process. The learning process is trained to learn to learn recursions between time series sets of SMT counter values and labeled error types. Once trained, a checkpoint of the learning model is deployed as an inference model and used to predict the likely occurrence of errors before the errors occur. Predicted errors are logged into a proactive service request queue, and feedback related to the predicted errors are used as feedback to continue training the learning process.
    Type: Grant
    Filed: October 13, 2022
    Date of Patent: June 17, 2025
    Assignee: Dell Products, L.P.
    Inventors: Owen Martin, Ramesh Doddaiah
  • Patent number: 12333774
    Abstract: A method of improving an efficiency of forming the golden samples obtains an image with a chip. Position information of the chip in the image is obtained based on the image. A target region on the image is labeled based on the position information. The target region is a region of the image covered by the chip. The target region is cut from the image to obtain a golden sample. An image process apparatus is also provided.
    Type: Grant
    Filed: July 19, 2022
    Date of Patent: June 17, 2025
    Assignee: HON HAI PRECISION INDUSTRY CO., LTD.
    Inventor: Tsung-Hsien Tsai
  • Patent number: 12327396
    Abstract: There are provided an image processing device, an image processing method, and a program that can accurately select normal images suitable for learning without visually selecting learning data by a human. An image processing device includes a processor, and the processor acquires an examination video picked up by an endoscope apparatus, acquires instructional information of the endoscope apparatus in the pickup of the examination video, specifies a learning frame section from a plurality of frames forming the examination video on the basis of the instructional information, and outputs a frame group of the learning frame section as first learning data.
    Type: Grant
    Filed: September 7, 2022
    Date of Patent: June 10, 2025
    Assignee: FUJIFILM Corporation
    Inventor: Takuya Tsutaoka
  • Patent number: 12299857
    Abstract: Embodiments of the present disclosure provide for improved generation and outputting of object identification data indicating object classifications for object representations. Such objects representations may correspond to depictions of objects in images captured using digital holographic microscopy. Some embodiments generate object identification data by comparing object representations in focused image(s) with specially configured annotated focused images, for example using a specially trained neural network or other machine learning model trained based on such annotated focused images. The annotated focused images are generated including a plurality of channels, each associated with a different grayscale focused image at a different target focal length of a range of target focal lengths. In this regard, model(s), algorithm(s), and/or other specially configured implementations may learn the spatial features of particular object representations and associated object identification data.
    Type: Grant
    Filed: July 21, 2022
    Date of Patent: May 13, 2025
    Assignee: Honeywell International Inc.
    Inventors: Andrey Shtylenko, Andy Walker Brown, Adam Dewey McBrady, Ratna Dinakar Tumuluri
  • Patent number: 12300037
    Abstract: A determination system includes: a projection control unit that controls a projection unit to project a random marker within an angle of view of an imaging unit; an acquisition unit that obtains an image of a target person including the marker from the imaging unit; and a determination unit that determines whether or not the target person imaged by the imaging unit is a living body on the basis of a state of the marker included in the image. According to such a determination system, it is possible to accurately determine whether or not the target person is a living body. Therefore, for example, it is possible to avoid a breakthrough of biometric authentication by an illegal method, or the like.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: May 13, 2025
    Assignee: NEC CORPORATION
    Inventor: Akihiro Hayasaka
  • Patent number: 12293517
    Abstract: Techniques described herein pertain to automated systems and methods for analyzing, storing, and/or retrieving information associated with biological objects including lymphocytes. In some embodiments, a shape metric is derived for each detected and segmented lymphocyte and the shape metric is stored along with other relevant data.
    Type: Grant
    Filed: October 30, 2023
    Date of Patent: May 6, 2025
    Assignee: VENTANA MEDICAL SYSTEMS, INC.
    Inventors: Joerg Bredno, Konstanty Korski, Oliver Grimm
  • Patent number: 12293500
    Abstract: An image inspection device which enables the user to know the cause of an abnormality in a read image. The image inspection device includes: an image reader outputting a read image generated by reading an image formed on a sheet of paper by an image forming device; an image inspection section inspecting the read image and outputting an inspection result which takes the read image determined not to have an abnormality as a normal image and the read image determined to have the abnormality as an abnormal image; an inspection result report generator generating an inspection result report according to the read image and the inspection result; an inspection result report output section outputting the inspection result report; and a controller performing control to cause the inspection result report output section to output the normal image and the abnormal image in a comparable manner.
    Type: Grant
    Filed: February 1, 2024
    Date of Patent: May 6, 2025
    Assignee: KONICA MINOLTA, INC.
    Inventor: Yasumasa Tsukamoto
  • Patent number: 12287992
    Abstract: A printing apparatus includes a reception unit configured to receive a print job, and an execution unit configured to execute printing of the print job received by the reception unit. The execution unit has a function of, in a case where a setting time or more elapses with a particular cause preventing the printing of the print job not being removed, canceling the printing of the print job. The execution unit has a function of canceling printing of a new print job received by the reception unit in a state where the setting time or more elapses with the particular cause not being removed.
    Type: Grant
    Filed: November 15, 2023
    Date of Patent: April 29, 2025
    Assignee: Canon Kabushiki Kaisha
    Inventor: Yuichi Yagi
  • Patent number: 12283091
    Abstract: The objective of the present invention is to provide an image classification device and a method therefor with which suitable teaching data can be created. An image classification device that carries out image classification using images which are in a class to be classified and include teaching information, and images which are in a class not to be classified and to which teaching information has not been assigned, said image classification device being characterized by being provided with: an image group input unit for receiving inputs of an image group belonging to a class to be classified and an image group belonging to a class not to be classified; and a subclassification unit for extracting a feature amount for each image in an image group, clustering the feature amounts of the images in the image group belonging to a class not to be classified, and thereby dividing the images into sub-classes.
    Type: Grant
    Filed: November 6, 2020
    Date of Patent: April 22, 2025
    Assignee: Hitachi High-Tech Corporation
    Inventors: Sota Komatsu, Masayoshi Ishikawa, Fumihiro Bekku, Takefumi Kakinuma
  • Patent number: 12272163
    Abstract: Systems and techniques are provided for unsupervised scene-decompositional normalizing flows. An example process can include obtaining a scene-decompositional model having a normalizing flow neural network architecture. The process can include determining, based on processing data depicting multiple targets in a scene using the scene-decompositional model, a distribution of scene data as a mixture of flows from one or more background components and one or more foreground components. The process can further include identifying, based on processing the distribution of scene data using the scene-decompositional model, a target associated with the one or more foreground components and included in the data depicting the multiple targets in the scene.
    Type: Grant
    Filed: July 7, 2022
    Date of Patent: April 8, 2025
    Assignee: QUALCOMM Incorporated
    Inventors: Farhad Ghazvinian Zanjani, Hanno Ackermann, Daniel Hendricus Franciscus Dijkman, Fatih Murat Porikli
  • Patent number: 12266103
    Abstract: One embodiment provides a method, the method including: obtaining, using at least one sensor of an information handling device facilitating a video conference, at least one image of a portion of a user of the information handling device participating in the video conference, wherein at least one participant in the video conference is located remotely with respect to the user; identifying, using an image diagnosis system, a condition of the portion of the user by analyzing the at least one image of the portion of the user; and transmitting, using the image diagnosis system, the condition to the at least one participant. Other aspects are claimed and described.
    Type: Grant
    Filed: June 30, 2022
    Date of Patent: April 1, 2025
    Assignee: Lenovo (Singapore) Pte. Ltd.
    Inventors: Sean C. Kelly, Koji Kawakita
  • Patent number: 12267471
    Abstract: An image forming apparatus includes an image forming unit configured to perform image formation on a sheet, a casing configured to house the image forming unit, an operation unit configured to receive an operation performed by a user, an electric wire extending from the casing to be connected to the operation unit and configured to transmit an electrical signal, a reinforcing member provided separate from and independent of the electric wire, the reinforcing member interconnecting the casing and the operation unit, and a covering configured to enclose therein the electric wire and the reinforcing member, wherein the reinforcing member is fixed to the casing and the operation unit in such a manner that a distance between a portion fixed to the casing and a portion fixed to the operation unit in the reinforcing member is shorter than a total length of the electric wire.
    Type: Grant
    Filed: December 4, 2023
    Date of Patent: April 1, 2025
    Assignee: Canon Kabushiki Kaisha
    Inventors: Yusaku Makino, Hirohisa Sawada, Shingo Hattori
  • Patent number: 12254689
    Abstract: An implement management system detects implement wear and monitors implement states to modify operating modes of a vehicle. The system can determine implement wear using the pull of the implement on the vehicle, the force and angle of which is represented by an orientation vector. The system may measure a current orientation vector and determine an expected orientation vector using sensors and a model (e.g., a machine learned model). Additionally, the implement management system can determine an implement state based on images of the soil and the implement captured by a camera onboard the vehicle during operation. The system may apply different models to the images to determine a likely state of the implement. The difference between the expected and current orientation vectors or the determined implement state may be used to determine whether and how the vehicle's operating mode should be modified.
    Type: Grant
    Filed: May 22, 2024
    Date of Patent: March 18, 2025
    Assignee: DEERE & COMPANY
    Inventors: Tyler D. Schleicher, Curtis A. Maeder, Noel W. Anderson, Jeffrey E. Runde
  • Patent number: 12254631
    Abstract: The techniques for dual-level semantic segmentation are provided. Data may be input to a first segmentation network. The input data comprises an image and label information associated with the image. The image may be captured at nighttime and may comprise a plurality of regions. At least one region among the plurality of regions may be determined based at least in part on output of the first segmentation network. The at least one region of the image may be cropped. The cropped at least one region may be input to a second segmentation network. A final output may be produced based on the output of the first segmentation network and output of the second segmentation network.
    Type: Grant
    Filed: January 26, 2022
    Date of Patent: March 18, 2025
    Assignee: Lemon Inc.
    Inventors: Peng Wang, Xueqing Deng, Xiaochen Lian
  • Patent number: 12254663
    Abstract: A method and system of recognizing and processing object edges and a computer-readable storage medium are provided. The method includes: obtaining an input image, where the input image includes an object with edges, and the edges of the object include a plurality of object vertices; recognizing, through an object vertex recognition model, the input image and obtaining a relative position of each object vertex and a corresponding image vertex thereof; determining an actual position of each object vertex in the input image according to the relative position of each object vertex and the corresponding image vertex thereof; and sequentially connecting adjacent object vertices to form edge lines to obtain the edges of the object with edges in the input image according to the actual position of each object vertex in the input image.
    Type: Grant
    Filed: July 21, 2021
    Date of Patent: March 18, 2025
    Assignee: Hangzhou Glority Software Limited
    Inventors: Qingsong Xu, Qing Li
  • Patent number: 12243299
    Abstract: An object tracking apparatus (1) includes: a first generation unit (221-224) for generating, based on a first position information (PIt-?) related to a position of an object (Ot-?) in a first image (IMt-?) captured at a first time (t-?) and a second position information (PIt) related to a position of an object (Ot) in a second image (IMt) captured at a second time (t), first and second feature vectors (CVt-?, CVt); and a second generation unit (225) for generating, as a correspondence information (AM) indicating a correspondence relationship between the object in the first image and the object in the second image, an information that is obtained by a calculation processing using the first and the second feature vectors.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: March 4, 2025
    Assignee: NEC CORPORATION
    Inventor: Hiroshi Fukui