Face Recognition Based on Gabor Wavelet Transform and Modular 2DPCA

Since the dimension of face features which is presented by Gabor wavelet is too high, there has large computation if using the feature by Gabor wavelet transform for recognition directly. A novel idea based on Gabor wavelet transform and modular Two-principal component analysis for face recognition is proposed. Firstly, face image feature is acquired by Gabor Wavelet transforming. Secondly, its dimension is reduced and eigenvectors are extracted by the method of modular 2DPCA. Finally, fusion with nearest neighbor classifier and support vector machine (SVM) is adopted to sort and distinguish. Experimental results on ORL and YALE show that the performance of proposed method is superior to other methods, such as modular 2DPCA and combination of Gabor wavelet transform and 2DPCA.