Record Details

Pace recognition using a DCT-HMM approach

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Pace recognition using a DCT-HMM approach
 
Creator KOHIR, VV
DESAI, UB
 
Description 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.
 
Publisher IEEE COMPUTER SOC
 
Date 2011-10-27T09:30:12Z
2011-12-15T09:12:32Z
2011-10-27T09:30:12Z
2011-12-15T09:12:32Z
1998
 
Type Proceedings Paper
 
Identifier FOURTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION - WACV'98, PROCEEDINGS,226-231
0-8186-8606-5
http://dspace.library.iitb.ac.in/xmlui/handle/10054/16250
http://hdl.handle.net/100/2730
 
Source 4th IEEE Workshop on Applications of Computer Vision (WACV 98),PRINCETON, NJ,OCT 19-21, 1998
 
Language English