Title :
Face Recognition System by Fast and Incremental Learning Method
Author :
Kang, Woo-Sung ; Na, Jin Hee ; Ahn, Ho Seok ; Choi, Jin Young
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Seoul Nat. Univ.
Abstract :
This paper introduces the face recognition system architecture based on intelligent macro core for face recognition. And we propose a novel classification method based on support vector domain description (SVDD). It enables the proposed system to be trained rapidly and improve the recognition rate gradually by learning face incrementally. In order to verify the performance of our scheme in real world, experiments are carried out under various illumination condition. The experimental results show that the proposed system can improve the recognition rate gradually by fast and incremental learning method
Keywords :
face recognition; image classification; learning (artificial intelligence); support vector machines; face recognition system architecture; image classification; incremental learning method; intelligent macro core; support vector domain description; Automation; Computer architecture; Computer science; Electronic mail; Face detection; Face recognition; Feature extraction; Learning systems; Lighting; Principal component analysis; Face Recognition; Fast Training; Incremental Learning;
Conference_Titel :
SICE-ICASE, 2006. International Joint Conference
Conference_Location :
Busan
Print_ISBN :
89-950038-4-7
Electronic_ISBN :
89-950038-5-5
DOI :
10.1109/SICE.2006.315028