Hand Written English Character Recognition using Row- wise Segmentation Technique (RST)

Due to the limitations in single layer ANN researchers started losing interest in ANN during 1970s. Later on the development of multiple layer neural networks led to the development of many efficient techniques to recognize hand written/printed characters with great accuracies and also making the technology complex and costly. In this paper an effort was made to recognize hand written English alphabets using single layer ANN. This approach makes the ANN simple, easy to implement and understand. Row-wise segmentation technique was developed and used here to achieve optimum accuracy. This paper is an approach to develop a method to get the optimized results using the easily available resources. Row-wise segmentation helps to extract out some common features among distinct handwriting styles of different people. General Terms Character recognition, Input pattern matrix, Weight matrix, Target group, Row wise Segmentation, Training, Learning rule, Distorted patterns, Counter.