Paper Details: Downloads: 668
Serial Number: P1151113541
Title: Face Recognition Using Wavelet Moments and Fast Wavelet Transform
Authors: Ali Mohammed Sahan
Abstract: In this paper we present face recognition method using a combination of fast wavelet transform and wavelet moments. The role of fast wavelet transform is to decompose the original image into different frequency sub-bands and removes the redundancy and to preserve the original features of the face image. In order to speed up and increase the accuracy of the proposed face recognition system, we keep only the coefficients of the approximation sub-band and discard the other sub-bands coefficients to feed the next stage wavelet moments. The proposed method is tested on the ORL face database which contains large variability in facial expression, illumination and pose. The proposed method has been compared with wavelet moments and Zernike moments. The results of the experiments indicate that the proposed method is better than both Zernike moments and wavelet moments in the recognition rate and the speed of the face recognition system
Keywords: Face recognition, wavelet transform, wavelet moments, Zernike moments
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 11
Issue: 3
Submission Date: 4/1/2011 12:00:00 AM
Review Date: 5/8/2011 12:00:00 AM
Publishing Date: 6/11/2011 12:00:00 AM
Article Downloads: 668
Download:

Facebook