Patents by Inventor Yongqiang Bai

Yongqiang Bai 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).

  • Patent number: 11995901
    Abstract: A method and a system for detecting a scene text are provided. The method includes: acquiring a scene text picture in a preset manner, pre-processing the acquired scene text picture, detecting the pre-processed scene text picture with a training model for scene text detection, and acquiring a detection result. Accordingly, the method and the system have an original PSENet (Progressive Scale Expansion Network) backbone network ResNet (Deep Residual Network) is replaced with a rich feature structure network (i.e. Res2NeXt (Combination of Res2Net and ResNeXt)) to improve a network feature extraction capability, thereby increasing a text detection precision of the network; mixed pooling is added at an appropriate location in the backbone network to acquire useful context information by performing pooling operations of different kernel shapes and capture long and short distance dependency relationships between different locations, thereby further increasing the text detection precision of the network.
    Type: Grant
    Filed: December 29, 2021
    Date of Patent: May 28, 2024
    Assignee: Zhejiang Wanli University
    Inventors: Zhongjie Zhu, Guanglong Liao, Yongqiang Bai, Yuer Wang
  • Publication number: 20220207890
    Abstract: A method and a system for detecting a scene text are provided. The method includes: acquiring a scene text picture in a preset manner, pre-processing the acquired scene text picture, detecting the pre-processed scene text picture with a training model for scene text detection, and acquiring a detection result. Accordingly, the method and the system have an original PSENet (Progressive Scale Expansion Network) backbone network ResNet (Deep Residual Network) is replaced with a rich feature structure network (i.e. Res2NeXt (Combination of Res2Net and ResNeXt)) to improve a network feature extraction capability, thereby increasing a text detection precision of the network; mixed pooling is added at an appropriate location in the backbone network to acquire useful context information by performing pooling operations of different kernel shapes and capture long and short distance dependency relationships between different locations, thereby further increasing the text detection precision of the network.
    Type: Application
    Filed: December 29, 2021
    Publication date: June 30, 2022
    Applicant: Zhejiang Wanli University
    Inventors: Zhongjie Zhu, Guanglong Liao, Yongqiang Bai, Yuer Wang
  • Patent number: 10368051
    Abstract: A 3D-HEVC inter-frame information hiding method based on visual perception includes steps of information embedding and information extraction. In the step of information embedding, the human visual perception characteristic is considered, stereo salient images are obtained by a stereo image salient model, and the stereo salient images are divided into salient blocks and non-salient blocks with an otsu threshold. The coding quantization parameters are modified according to different modulation rules for different regions. Then, based on the modified quantization parameters, the coding-tree-units are coded to complete the information embedding. In the step of information extraction, no original video is needed, no any side information needs to be transmitted, and the secret information can be blindly extracted.
    Type: Grant
    Filed: August 25, 2017
    Date of Patent: July 30, 2019
    Assignee: Ningbo University
    Inventors: Gangyi Jiang, Jing Wang, Fen Chen, Yongqiang Bai, Yang Wang
  • Patent number: 10297000
    Abstract: A high dynamic range image information hiding method includes embedding secret information and extracting the secret information. The step of embedding secret information includes obtaining three channel values of every pixel in an original high dynamic range image; according to every channel value and corresponding 5-bit exponent of every pixel, determining an embedding significance bit of the information to be embedded in every channel value of every pixel; embedding information into every channel value of every pixel; and obtaining a high dynamic range image embedded with the secret information.
    Type: Grant
    Filed: November 8, 2017
    Date of Patent: May 21, 2019
    Assignee: Ningbo University
    Inventors: Gangyi Jiang, Yongqiang Bai, Mei Yu, Yang Wang
  • Publication number: 20180075569
    Abstract: A high dynamic range image information hiding method includes embedding secret information and extracting the secret information. The step of embedding secret information includes obtaining three channel values of every pixel in an original high dynamic range image; according to every channel value and corresponding 5-bit exponent of every pixel, determining an embedding significance bit of the information to be embedded in every channel value of every pixel; embedding information into every channel value of every pixel; and obtaining a high dynamic range image embedded with the secret information.
    Type: Application
    Filed: November 8, 2017
    Publication date: March 15, 2018
    Inventors: Gangyi Jiang, Yongqiang Bai, Mei Yu, Yang Wang
  • Publication number: 20170374347
    Abstract: A 3D-HEVC inter-frame information hiding method based on visual perception includes steps of information embedding and information extraction. In the step of information embedding, the human visual perception characteristic is considered, stereo salient images are obtained by a stereo image salient model, and the stereo salient images are divided into salient blocks and non-salient blocks with an otsu threshold. The coding quantization parameters are modified according to different modulation rules for different regions. Then, based on the modified quantization parameters, the coding-tree-units are coded to complete the information embedding. In the step of information extraction, no original video is needed, no any side information needs to be transmitted, and the secret information can be blindly extracted.
    Type: Application
    Filed: August 25, 2017
    Publication date: December 28, 2017
    Inventors: Gangyi Jiang, Jing Wang, Fen Chen, Yongqiang Bai, Yang Wang