DocumentCode :
2799225
Title :
Face recognition across different poses using a single 2D model view
Author :
Du, Cheng ; Su, Guangda ; Lin, Xinggang
Author_Institution :
Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
Volume :
2
fYear :
2003
fDate :
8-13 Oct. 2003
Firstpage :
721
Abstract :
The pose problem is a difficult area of face recognition. Until now, we haven´t had a good method to tackle the problem. In this paper, a simple fronto-parallel face recovery method is presented, the method is simple and effective, it addresses the computationally expensive problem of current 3-D model pose recovery methods, experiments showed that the method can greatly enhance the recognition rate.
Keywords :
face recognition; 3D model pose recovery method; computationally expensive problem; face recognition; fronto parallel face recovery method; recognition rate; single 2D model; Automatic control; Computer graphics; Face detection; Face recognition; Head; Humans; Image databases; Image recognition; Information security; Laboratories;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003 IEEE International Conference on
Print_ISBN :
0-7803-7925-X
Type :
conf
DOI :
10.1109/RISSP.2003.1285673
Filename :
1285673
Link To Document :
بازگشت