Record Details

A transform domain face recognition approach

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title A transform domain face recognition approach
 
Creator KOHIR, VV
DESAI, UB
 
Subject discrete cosine transforms
face recognition
hidden markov models
image sampling
image sequences
 
Description The paper combines DCT (discrete cosine transform) and HMM (hidden Markov model) to realise a face recognition technique. The face images are subsampled to obtain a sequence of face sub-images. Each sub-image is DCT transformed and the coefficients are scanned (similar to the JPEG image compression method) to form a vector. These vectors are applied to HMMs for recognition. Two different face databases-ORL and SPANN are used. The recognition rate for ORL is 99.5% with 5 training and 5 testing images per subject. The SPANN database has a recognition rate of 98.75% with 3 training images and 4 test images per subject. Further, an investigation into dependence of recognition rate on number of training images, and number of HMM states.
 
Publisher IEEE
 
Date 2008-12-15T10:38:31Z
2011-11-27T12:39:59Z
2011-12-15T09:56:20Z
2008-12-15T10:38:31Z
2011-11-27T12:39:59Z
2011-12-15T09:56:20Z
1999
 
Type Article
 
Identifier TENCON'99: Proceedings of the IEEE Region 10 Conference on Multimedia Technology for Asia-Pacific Information Infrastructure (V 1), Cheju Island, Korea, 15-17 September 1999, 104-107
0-7803-5739-6
10.1109/TENCON.1999.818360
http://hdl.handle.net/10054/325
http://dspace.library.iitb.ac.in/xmlui/handle/10054/325
 
Language en