TY - GEN
T1 - Local appearance based face recognition using discrete cosine transform
AU - Ekenel, Hazim Kemal
AU - Stiefelhagen, Rainer
PY - 2005
Y1 - 2005
N2 - In this paper, a local appearance based face recognition algorithm is proposed. In the proposed algorithm local information is extracted using block-based discrete cosine transform. Obtained local features are combined both at the feature level and at the decision level. The performance of the proposed algorithm is tested on the Yale and CMU PIE face databases, and the obtained results show significant improvement over the holistic approaches.
AB - In this paper, a local appearance based face recognition algorithm is proposed. In the proposed algorithm local information is extracted using block-based discrete cosine transform. Obtained local features are combined both at the feature level and at the decision level. The performance of the proposed algorithm is tested on the Yale and CMU PIE face databases, and the obtained results show significant improvement over the holistic approaches.
UR - http://www.scopus.com/inward/record.url?scp=84863693528&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863693528&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84863693528
SN - 1604238216
SN - 9781604238211
T3 - 13th European Signal Processing Conference, EUSIPCO 2005
SP - 2484
EP - 2488
BT - 13th European Signal Processing Conference, EUSIPCO 2005
T2 - 13th European Signal Processing Conference, EUSIPCO 2005
Y2 - 4 September 2005 through 8 September 2005
ER -