Face recognition using Symlet, PCA and cosine angle distance measure

In this paper an approach for face recognition is proposed using Symlet, PCA and Cosine angle distance measure. The recognition rate and computational cost of proposed approach is examined against different wavelet families and Euclidean distance measure. Feature extraction is performed using Discrete wavelet transform and Principal component analysis (DWT-PCA). In order to explore best features, experiments are carried out for DWT subband selection and for DWT wavelet selection on Symlet family and on four other different wavelet families (Daubechies, Coiflets, Discrete Meyer and Biorthogonal wavelet family). This also includes their members that vary in terms of orthogonality, symmetry, support size, vanishing moments and filter order. After generating feature vectors, classification is done by Cosine angle distance measure based nearest neighbor classifier (NNC) and its results are compared with Euclidean distance measure. As test dataset, AT&T database of 400 images of 40 people is used to establish the performance by proposed approach. Experimental results on Symlet-6 with Cosine angle distance measure based nearest neighbor classifier shows highest percentage recognition rate of 98.33 for randomly generated 120 image training set.