Audio-Assisted Video Based Face Recognition
- Summary
- In this work, we develop a new audio-assisted video-to-video face recognition algorithm. The major advantage of the video based method is that more information is available in a video sequence than in a single image. In order to take full advantage of the large amount of information in the video sequence and at the same time overcome the processing speed and data size problems we develop several new techniques including temporal and spatial frame synchronization, multi-level subspace analysis, and multi-classifier integration for video cube processing. The method preserves all the spatial-temporal information contained in a video sequence. Near perfect classification results are obtained on the XM2VTS face video database.
- Supplementary Information
- Inventor: Xiaoou Tang
Priority Number: CN1866270B
IPC Current: G06K000900
Assignee Applicant: The Chinese University of Hong Kong
Title: Face recognition method based on video frequency | Based on face identifying method of video
Usefulness: Face recognition method based on video frequency | Based on face identifying method of video
Novelty: Face recognition method based on video frequency
- Industry
- ICT/Telecom
- Sub Category
- Image Processing
- Application No.
- 04/ENG/183
- Others
- Inventor(s): Professor Xiaoou TANG, Department of Information Engineering
Licensing Status: Available for licensing
Patent Status: Chinese Patent Pending Hong Kong Patent Pending
- Country/Region
- Hong Kong
For more information, please click Here