DocumentCode :
3267471
Title :
Real-time image processing of human face identification for home service robot
Author :
Wang, Ying-Hao ; Shih, Yen-Te ; Cheng, K. -C ; Lin, Chih-Jui ; Li, Tzuu-Hseng S.
Author_Institution :
Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan
fYear :
2011
fDate :
20-22 Dec. 2011
Firstpage :
1171
Lastpage :
1176
Abstract :
This paper presents a real-time image processing of human face identification for home service robot (HSR). This vision system is set up by two individual sub-systems. The first one is face detection and tracking sub-system based on adaptive skin detector, condensation filter with parallel computing particles, and Haar-like classifier. And a simple and fast motion predictor is also proposed for face tracking. The second is face recognition system based on embedded HMM (EHMM) with parallel training and recognition procedures. In order to reach a fast, robust, efficient, this study used extensible parallel integrated vision system (PIVS). Finally, real-time experimental results on different humans in different unknown scenes demonstrate that the proposed PIVS is indeed feasible, simple and safe.
Keywords :
Haar transforms; face recognition; filtering theory; hidden Markov models; motion compensation; object tracking; robot vision; service robots; EHMM; HSR; Haar-like classifier; PIVS; adaptive skin detector; condensation filter; embedded HMM; extensible parallel integrated vision system; face detection; face recognition system; face tracking subsystem; home service robot; human face identification; individual subsystems; motion predictor; parallel computing particles; parallel training; real-time image processing; recognition procedures; Face; Face detection; Face recognition; Hidden Markov models; Humans; Image color analysis; Skin;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
System Integration (SII), 2011 IEEE/SICE International Symposium on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4577-1523-5
Type :
conf
DOI :
10.1109/SII.2011.6147615
Filename :
6147615
Link To Document :
بازگشت