Invention Grant
US08879799B2 Human identification system by fusion of face recognition and speaker recognition, method and service robot thereof
有权
人体识别系统通过融合人脸识别和说话者识别，其方法和服务机器人
- Patent Title: Human identification system by fusion of face recognition and speaker recognition, method and service robot thereof
- Patent Title (中): 人体识别系统通过融合人脸识别和说话者识别，其方法和服务机器人
-
Application No.: US13675590Application Date: 2012-11-13
-
Publication No.: US08879799B2Publication Date: 2014-11-04
- Inventor: Kai-Tai Song , Shuo-Cheng Chien , Chao-Yu Lin , Yi-Wen Chen , Sin-Horng Chen , Chen-Yu Chiang , Yi-Chiao Wu
- Applicant: National Chiao Tung University
- Applicant Address: TW Hsinchu
- Assignee: National Chiao Tung University
- Current Assignee: National Chiao Tung University
- Current Assignee Address: TW Hsinchu
- Agency: Muncy, Geissler, Olds & Lowe, P.C.
- Priority: TW101125278A 20120713
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G10L17/00 ; G10L17/06
Abstract:
The present invention discloses a human identification system by fusion of face recognition and speaker recognition, a method and a service robot thereof. The system fuses results of the face recognition and the speaker recognition, and further uses confidence index to estimate the confidence level of the two recognition results. If only one of the confidence indices of the two recognition results reaches the threshold, then only this result is used as the output. If both confidence indices of the two recognition results reach the threshold, then the two recognition results are fused to output as a final result.
Public/Granted literature
Information query
