Face recognition using a DCT-HMM approach

Author

Kohir, Vinayadatt V. ; Desai, U.B.

Author_Institution

Dept. of Electr. Eng., Indian Inst. of Technol., Mumbai, India

fYear

1998

fDate

19-21 Oct 1998

Firstpage

226

Lastpage

231

Abstract

A transform domain approach coupled with Hidden Markov Model (HMM) for face recognition is presented. JPEG kind of strategy is employed to transform input subimage for training HMMs. DCT transformed vectors efface images are used to train ergodic HMM and later for recognition. ORL face database of 40 subjects with 10 images per subject is used to evaluate the performance of the proposed method. 5 images per subject are used for training and the rest 5 for recognition. This method has an accuracy of 99.5%. The results, to the best of knowledge of the authors, give the best recognition percentage as compared to any other method reported so far on ORL face database

Keywords

discrete cosine transforms; face recognition; hidden Markov models; DCT transformed vectors; JPEG; face database; face recognition; hidden Markov model; performance; transform domain approach; Artificial neural networks; Discrete cosine transforms; Educational institutions; Face recognition; Hidden Markov models; Image databases; Image recognition; Laboratories; Statistical analysis; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Applications of Computer Vision, 1998. WACV '98. Proceedings., Fourth IEEE Workshop on

Conference_Location

Princeton, NJ

Print_ISBN

0-8186-8606-5

Type

conf

DOI

10.1109/ACV.1998.732884

Filename

732884