FPGA Implementation of Feature Extraction and MLP Neural Network Classifier for Farsi Handwritten Digit Recognition

Abstract

An accurate method for feature extraction based on FPGA (Field Programmable Gate Arrays) implementation is proposed in this paper. The specific application is offline Farsi handwritten digit recognition. The classification is based on a simple two layer MLP (Multi Layer Perceptron). This method of feature extraction is appropriate for FPGA implementation as it can be implemented only with add and subtract operations. This greatly speeds up the process. The proposed method is used to extract the features from normalized 40*40 pixel handwritten digit images. Applying this method to a Farsi digit recognition system is implemented using a two-layer MLP artificial neural network with few neurons in the hidden layer. The system is simple, more accurate and less complex than the other similar systems.