中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.013 seconds)

    Steganography method
    1.
    发明授权
    Steganography method 有权

    公开(公告)号：US12147550B2

    公开(公告)日：2024-11-19

    申请号：US17897246

    申请日：2022-08-29

    Applicant: Defense Agency for Technology and Quality

    Inventor： Jin Woo Ahn ,  Sang Woo Noh ,  Tae Hwan Kim

    IPC: G06F21/60 ,  G06N3/045 ,  G06N3/08 ,  G06V10/74 ,  G06V10/82 ,  G06V20/00 ,  H04N19/467

    Abstract: A steganography method and an apparatus embedding a hidden message in a video stream of an original cover video to produce a stego video using a generative neural network. The original cover video is a video stream as opposed using an image. A discriminant neural network is used to correct a generated video compared to an original cover video. The generated neural network is trained when the generated video is determined to be real by the discriminant neural network. A second stego video is acquired by adversarial training through a mutually adversarial relationship between a generative neural network and an discriminant neural network. The embedding technique is one of pre-embedding, intra-embedding, or post-embedding.

    Method for creating hyperspectral high speed camera image using generative adversarial network algorithm
    2.
    发明授权
    Method for creating hyperspectral high speed camera image using generative adversarial network algorithm 有权

    公开(公告)号：US12143698B2

    公开(公告)日：2024-11-12

    申请号：US17558835

    申请日：2021-12-22

    Applicant: Defense Agency for Technology and Quality

    Inventor： Sang Woo Noh ,  Tae Hwan Kim ,  Jin Woo Ahn ,  Han Gyu Kim

    IPC: H04N23/11 ,  G06T7/00

    Abstract: A method creating a high-speed hyperspectral video by acquiring images from a hyperspectral high speed camera and forming a of a three-dimensional data cube by including spectra for each pixel in addition to a two-dimensional spatial information of an image taken with a general camera. Dividing successive three-dimensional data cubes obtained by photographing images with a spectral scanning type hyperspectral camera. Acquiring the three-dimensional data cubes for each specific time point and creating three-dimensional data cubes for as many as the number of spectra. Then separating a region corresponding to a moving object and a region corresponding to a background from the created data cubes. Acquiring spectral values according to spatial locations of the images and reconstructing a three-dimensional data cube with all spectral values for each specific time point with regard to the region with motion through a generative adversarial network algorithm.

    Method for synthesizing image
    5.
    发明授权
    Method for synthesizing image 有权

    公开(公告)号：US11983843B2

    公开(公告)日：2024-05-14

    申请号：US17549944

    申请日：2021-12-14

    Applicant: Defense Agency for Technology and Quality

    Inventor： Sang Woo Noh ,  Tae Hwan Kim ,  Jin Woo Ahn ,  Han Gyu Kim

    IPC: G06K9/00 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4007 ,  G06T3/4046 ,  G06T5/50

    CPC classification number: G06T3/4007 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4046 ,  G06T5/50

    Abstract: The present application relates to a method for synthesizing image and an image synthesizing apparatus using the same. The image synthesizing method of the present application and the image synthesizing apparatus using the same can reduce the time required for learning by reducing the distortion phenomenon of the algorithm and reducing the amount of calculation required for image synthesis. In addition, the image synthesizing method of the present application and the image synthesizing apparatus using the same can be utilized in various fields such as national defense, IT, and entertainment based on characteristics such as excellent performance and learning time reduction of deep learning algorithms, and can be utilized in psychological warfare or induction of command system confusion.

Patent Agency Ranking