Single Modal Transform Domain Face Recognition Based On DWT And FFT

Authors : Rangaswamy Y and Prashanth C R

Abstracts

The physiological biometric characteristics are better compared to behavioral biometric identification of human beings to identify a person. In this paper, we propose Single Modal Transform Domain Face Recognition Method Based on DWT and FFT. The original Face image is cropped and resized to suitable dimension to apply DWT. The FFT is applied on LL band approximation coefficients of DWT to get Face features. The Euclidean Distance(ED) is used to compare features of test face image with database images. Performance analysis shows that the values of False Rejection Rate(FRR), False Acceptance Rate(FAR) and Total Success Rate(TSR) are better in the proposed method compare to Existing Methods. 

Keywords: Face recognition, DWT/FFT; Euclidean Distance; Pre-processing.