Patents by Inventor Cheng-hsu Lee

Cheng-hsu Lee 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).

  • Systems and methods for foreground and background processing of content in a live video
    Patent number: 11386562
    Abstract: A computing device generates a user interface that includes a viewing window and a toolbar including a selection tool. The computing device displays a live video depicting one or more individuals in the viewing window of the user interface and generates a segmentation mask for each individual depicted in the live video, where each segmentation mask comprises facial feature vectors of a facial region of each individual. The computing device obtains selection of an individual depicted in the live video and compares facial feature vectors of each of the individuals depicted in the live video with the facial feature vector of the selected individual. The computing device converts the segmentation masks of individuals with corresponding facial feature vectors that do not match the selected facial feature vector to a filter mask and composites the filter mask with a background content of the live video.
    Type: Grant
    Filed: December 3, 2019
    Date of Patent: July 12, 2022
    Assignee: CYBERLINK CORP.
    Inventors: Ming-Hung Chiang, Cheng-hsu Lee
  • SYSTEMS AND METHODS FOR FOREGROUND AND BACKGROUND PROCESSING OF CONTENT IN A LIVE VIDEO
    Publication number: 20200211201
    Abstract: A computing device generates a user interface that includes a viewing window and a toolbar including a selection tool. The computing device displays a live video depicting one or more individuals in the viewing window of the user interface and generates a segmentation mask for each individual depicted in the live video, where each segmentation mask comprises facial feature vectors of a facial region of each individual. The computing device obtains selection of an individual depicted in the live video and compares facial feature vectors of each of the individuals depicted in the live video with the facial feature vector of the selected individual. The computing device converts the segmentation masks of individuals with corresponding facial feature vectors that do not match the selected facial feature vector to a filter mask and composites the filter mask with a background content of the live video.
    Type: Application
    Filed: December 3, 2019
    Publication date: July 2, 2020
    Inventors: Ming-Hung Chiang, Cheng-hsu Lee