Abstract
This work presents a method to increase the face recognition accuracy using a combination of Wavelet, PCA, KPCA, and RBF Neural Networks. Preprocessing, feature extraction and classification rules are three crucial issues for face recognition. This paper presents a hybrid approach to employ these issues. For preprocessing and feature extraction steps, we apply a combination of wavelet transform, PCA and KPCA. During the classification stage, the Neural Network (RBF) is explored to achieve a robust decision in presence of wide facial variations. At first derives a feature vector from a set of downsampled wavelet representation of face images, then the resulting PCA-based linear features and KPCA- based nonlinear features on wavelet feature vector for reduces the dimensionary of the vector, are extracted. During the classification stage, the Neural Network (RBF) is explored to achieve a robust decision in presence of wide facial variations. The computational load of the proposed method is greatly reduced as comparing with the original PCA, KPCA, ICA and LDA based method on the ORL, Yale and AR face databases. Moreover, the accuracy of the proposed method is improved.