Please use this identifier to cite or link to this item:
Title: A transform domain face recognition approach
Authors: KOHIR, VV
Keywords: Discrete Cosine Transforms
Face Recognition
Hidden Markov Models
Image Sampling
Image Sequences
Issue Date: 1999
Publisher: IEEE
Citation: 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
Abstract: 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.
URI: 10.1109/TENCON.1999.818360
ISBN: 0-7803-5739-6
Appears in Collections:Proceedings papers

Files in This Item:
File Description SizeFormat 
17685.pdf533.08 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.