A Novel Approach for Facial Feature Extraction in Face Recognition

Face recognition is the process of identifying a person by comparing his facial image with the existing image in a trained database. The crucial step in face recognition system is the extraction of facial feature. We propose an efficient facial feature representation by using Dual Tree Complex Wavelet Transform (DT-CWT). The Complex WT face characterizes the geometrical structure of facial images by using the properties of DT-CWT such as approximate shift in-variance and good directional selectivity. Since the efficiency retained with DT-CWT is inadequate, a new block design using Dual Tree Complex Wavelet Transform along with efficient normalization and noise reduction techniques is developed and using that design a face recognition system is developed.