Face Recognition Based Wavelet-PCA Features and Skin Color Model

Abstract

In this paper, a face recognition system for personal identification using Discret Wavelet Transform(DWT), Principle component Analysis (PCA) and Back-propagation Neural Network is proposed. The system consists of three steps. In first step pre-processing (de-noising and face detection based on skin color in RGB color space) are applied on the input image. The DWT is used to generate the feature images from individual wavelet sub bands. Only the low frequency band constructed from Wavelet Coefficients are used as a feature vector for the further process. The Principal Component Analysis (PCA) is used to reduce the dimensionality of the feature vector. Reduced feature vector are used for further classification using neural network Classifier. The proposed approaches are tested on a number of face images. Experimental results demonstrate the higher degree performance of this algorithm.