Hardware directed fast eigenface based face detection algorithm using FFT

This paper describes a hardware oriented algorithm for eigenface based face detection using FFT. Eigenfaces have long been used for face detection and recognition and are known to give reasonably good results. But, the distance from face space is not a completely reliable measure to detect faces. We have derived the FFT-based computation of distance measure which facilitates hardware implementation and fast face detection. We have also extended the face detection framework by training with the whole face as well as other facial features like eyes, mouth etc. separately. The basis eigen vectors are obtained for face features and by combining the distance measure obtained in each case separately, better classification is obtained.