Feature Extraction and Recognition of Handwritten English Character Using Artificial Neural Network

Abstract

This paper presents the development of English Handwritten character recognition system, which uses local and global features of English characters by applying the concept of feature feeding. After each character is extracted, the features are fed to the recognition engine. A well-known Multi-layer Feedforward neural network with backpropagation learning algorithm is chosen for its fast processing time and its good performance for pattern recognition problems. Backpropagation Learning algorithm is prefered for training of neural network. Training set occurs of various English characters collected from different people. The characters are presented directly to the network and correctly sized in pre-processing. In applying with free-hand English single characters, the average recognition rate of 91% has been achieved this confirms that the proposed approach is suitable for the development of English handwritten character recognition system. Recognition percentage of the system is higher than acceptable level. Input data, network parameters and training period affect the result.