Face recognition using RBF neural networks and wavelet transform

Recently, wavelet transform and image fusion mechanism have been used in face recognition to improve the performance. In this paper, we propose a new face recognition method based on wavelet transform and radial basis function (RBF) fusion network. Firstly, an image is decomposed with wavelet transform (WT) to three levels. Secondly, the Fisherface method is applied to three low-frequency sub-images respectively. Then, the individual classifiers are fused using the RBF neural network. Experimental results show that the proposed method outperforms both individual classifiers and the direct Fisherface method.