A transform domain face recognition approach

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.