DocumentCode
698909
Title
Local appearance based face recognition using discrete cosine transform
Author
Ekenel, Hazim Kemal ; Stiefelhagen, Rainer
Author_Institution
Interactive Syst. Labs., Univ. of Karlsruhe, Karlsruhe, Germany
fYear
2005
fDate
4-8 Sept. 2005
Firstpage
1
Lastpage
5
Abstract
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.
Keywords
discrete cosine transforms; face recognition; CMU PIE face database; Yale; block-based discrete cosine transform; face recognition algorithm; local information extraction; Databases; Discrete cosine transforms; Face; Face recognition; Feature extraction; Principal component analysis; Training;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing Conference, 2005 13th European
Conference_Location
Antalya
Print_ISBN
978-160-4238-21-1
Type
conf
Filename
7078507
Link To Document