Patents by Inventor Chien-Wei Yeh

Chien-Wei Yeh has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250117174
    Abstract: The present invention provides an image data transmission method and an image processing module. The image data transmission method comprises following steps: separating an image data into a first part and a second part by an image processing module; outputting the first part and the second part from a first connection port and a second connection port of an image processing module to a third connection port and a fourth connection port of a computer device; combining the first part and the second part by a software driver layer of the computer device to obtain combined data; and decoding the combined data by an application layer of the computer device to display the image data. Wherein the first connection port and the second connection port have the same transmission specification, and the first part and the second part have the same size in each frame of the image data.
    Type: Application
    Filed: June 1, 2024
    Publication date: April 10, 2025
    Inventors: Cheng-Pin HUANG, Chien-Wei YEH
  • Patent number: 11170203
    Abstract: A training data generation method for human facial recognition and a data generation apparatus are provided. A large amount of virtual synthesized models are generated based on a face deformation model, where changes are made to face shapes, expressions, and/or angles to increase diversity of the training data. Experimental results show that the aforementioned training data may improve the accuracy of human face recognition.
    Type: Grant
    Filed: November 27, 2019
    Date of Patent: November 9, 2021
    Assignee: National Central University
    Inventors: Jia-Ching Wang, Chien-Wei Yeh
  • Publication number: 20210158020
    Abstract: A training data generation method for human facial recognition and a data generation apparatus are provided. A large amount of virtual synthesized models are generated based on a face deformation model, where changes are made to face shapes, expressions, and/or angles to increase diversity of the training data. Experimental results show that the aforementioned training data may improve the accuracy of human face recognition.
    Type: Application
    Filed: November 27, 2019
    Publication date: May 27, 2021
    Applicant: National Central University
    Inventors: Jia-Ching Wang, Chien-Wei Yeh