TY - GEN
T1 - Novel face recognition method using trend vector for a multimedia album
AU - Lee, Sung Ho
AU - Han, Jong Woo
AU - Kwon, Oh Jung
AU - Kim, Tae Hyun
AU - Ko, Sung Jea
PY - 2012
Y1 - 2012
N2 - Automatic recognition of faces in photos is a highly challenging task since face appearance varies with poses, expressions, and lighting conditions. In this paper, we introduce a novel face recognition method using the trend vector which consists of the distances between the probed feature vector with all reference feature vectors in the gallery. Experimental results show that the proposed method achieves higher recognition rate than the conventional methods under the aforementioned challenging conditions.
AB - Automatic recognition of faces in photos is a highly challenging task since face appearance varies with poses, expressions, and lighting conditions. In this paper, we introduce a novel face recognition method using the trend vector which consists of the distances between the probed feature vector with all reference feature vectors in the gallery. Experimental results show that the proposed method achieves higher recognition rate than the conventional methods under the aforementioned challenging conditions.
UR - http://www.scopus.com/inward/record.url?scp=84863351502&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863351502&partnerID=8YFLogxK
U2 - 10.1109/ICCE.2012.6161988
DO - 10.1109/ICCE.2012.6161988
M3 - Conference contribution
AN - SCOPUS:84863351502
SN - 9781457702310
T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
SP - 490
EP - 491
BT - 2012 IEEE International Conference on Consumer Electronics, ICCE 2012
T2 - 2012 IEEE International Conference on Consumer Electronics, ICCE 2012
Y2 - 13 January 2012 through 16 January 2012
ER -