Face recognition using a fuzzy-Gaussian neural network
Victor-Emil Neagoe, Iuliana F. Iatan · 2003
We present a face recognition approach using a new version of Chen and Teng's (1998) fuzzy neural network, which we have modified from an identifier into a neurofuzzy classifier called fuzzy-Gaussian neural network (FGNN). We have deduced modified equations for training the FGNN. Our presented face recognition cascade has two stages: (a) feature extraction using either principal component analysis (PCA) or the discrete cosine transform (DCT); and (b) pattern classification using the FGNN. We have performed software implementation of the algorithm and experimented the face recognition task for a database of 100 images (10 classes). The recognition score has been 100% (for the test lot) for almost all the considered variants of feature extraction. We have also compared the performances of the FGNN with those obtained using a classical multilayer fuzzy perceptron (FP). We can deduce a significant advantage of the proposed FGNN over FP.