High performance face recognition using PCA and ZM on fused LWIR and VISIBLE images on the wavelet domain

Real time face recognition systems have become an area of growing interest due to its wide area of applications. This paper exploits the energy compaction property of the wavelet transform to provide a high performance face recognition system using the PCA and ZM techniques on fused and DWT approximation sub band images. The experimental results indicate that the wavelet sub band images enhance the face recognition accuracy by 27.2% for the PCA technique and by 3.9% for the ZM technique. Results also indicate that the wavelet approximation sub band images reduce the computational time by 50% for the PCA and by 38.46% for the ZM technique.