DocumentCode :
1977295
Title :
Pose invariant face recognition
Author :
Huang, Fu Jie ; Zhou, Zhihua ; Zhang, Hong-Jiang ; Chen, Tsuhan
Author_Institution :
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
fYear :
2000
fDate :
2000
Firstpage :
245
Lastpage :
250
Abstract :
We describe a novel neural network architecture, which can recognize human faces with any view in a certain viewing angle range (from left 30 degrees to right 30 degrees out of plane rotation). View-specific eigenface analysis is used as the front-end of the system to extract features, and the neural network ensemble is used for recognition. Experimental results show that the recognition accuracy of our network ensemble is higher than conventional methods such as using a single neural network to recognize faces of a specific view
Keywords :
eigenvalues and eigenfunctions; face recognition; feature extraction; neural net architecture; feature extraction; neural network architecture; pose-invariant face recognition; view-specific eigenface analysis; Active appearance model; Data acquisition; Deformable models; Face recognition; Humans; Identity-based encryption; Image recognition; Independent component analysis; Neural networks; Neutron spin echo;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference on
Conference_Location :
Grenoble
Print_ISBN :
0-7695-0580-5
Type :
conf
DOI :
10.1109/AFGR.2000.840642
Filename :
840642
Link To Document :
بازگشت