TY - GEN
T1 - VQ-based face recognition algorithm using code pattern classification and Self-Organizing Maps
AU - Chen, Qiu
AU - Kotani, Koji
AU - Lee, Feifei
AU - Ohmi, Tadahiro
PY - 2008/12/1
Y1 - 2008/12/1
N2 - In this paper, an improved codebook design method is proposed for VQ-based fast face recognition algorithm to improve recognition accuracy. Combined by a systematically organized codebook based on the classification of code patterns abstracted from facial images and another codebook created by Kohonen 's Self-Organizing Maps (SOM) method, an optimized codebook consisted of 2x2 codevectors for facial images is generated. The performance of proposed algorithm is demonstrated by using publicly available AT&T database containing variations in lighting, posing, and expressions. Compared with the algorithms employing original codebook or SOM codebook separately, experimental results show face recognition using proposed codebook is more efficient. The highest average recognition rate of 98.6% is obtained for 40 persons' 400 images of AT&T database.
AB - In this paper, an improved codebook design method is proposed for VQ-based fast face recognition algorithm to improve recognition accuracy. Combined by a systematically organized codebook based on the classification of code patterns abstracted from facial images and another codebook created by Kohonen 's Self-Organizing Maps (SOM) method, an optimized codebook consisted of 2x2 codevectors for facial images is generated. The performance of proposed algorithm is demonstrated by using publicly available AT&T database containing variations in lighting, posing, and expressions. Compared with the algorithms employing original codebook or SOM codebook separately, experimental results show face recognition using proposed codebook is more efficient. The highest average recognition rate of 98.6% is obtained for 40 persons' 400 images of AT&T database.
UR - http://www.scopus.com/inward/record.url?scp=67249105799&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=67249105799&partnerID=8YFLogxK
U2 - 10.1109/ICOSP.2008.4697550
DO - 10.1109/ICOSP.2008.4697550
M3 - Conference contribution
AN - SCOPUS:67249105799
SN - 9781424421794
T3 - International Conference on Signal Processing Proceedings, ICSP
SP - 2059
EP - 2064
BT - 2008 9th International Conference on Signal Processing, ICSP 2008
T2 - 2008 9th International Conference on Signal Processing, ICSP 2008
Y2 - 26 October 2008 through 29 October 2008
ER -