Classification of handwritten alphanumeric characters: a fuzzy neural approach
Swaminathan Annadurai, A. Balasubramaniam · 2002
An efficient supervised feedforward fuzzy neural classifier (SFFNN) and its associated training algorithm for classification of handwritten English alphabets and arabic numerals are proposed in this paper. The utilized classifier is a five layer network and the number of the minimum fuzzy neurons in the third layer is dynamically organized during its training. This classifier learns the membership function values of each input image from the training set. Through extensive experimentation with noiseless and noisy binary images of English alphabets and ten Arabic numerals, it is found that the performance of the SFFNN is better than Yalings's fuzzy neural network (YFNN) and multilayer perceptron (MLP) network. The SFFNN after training, recognizes character images 98.7% accurately.