Facial Tilt and Image Background Challenges In Frequency Domain Face Recognition

In this paper facial tilt and varying background challenges to face recognition in frequency domain have been addressed and maximum possible compensation to these problems is provided in image pre processing through image reverse rotation and gray scale morphological operations. Facial features through two distinct techniques are extracted by applying discrete Fourier transform (DFT) on images. In this face recognition model only real part of DFT coefficients with maximum information is retained for recognition which not only provides considerable dimension reduction with improved computational speed but also better recognition results. Experiments on ORL and YALE datasets have been performed with success rate up to 98.78%