Chain Code Based Handwritten Cursive Character Recognition System with Better Segmentation Using Neural Network
Parikh Nirav Tushar, Saurabh Upadhyay · 2013
Character recognition plays an important role in many resent applications. Pattern recognition deals with categorization of input data. It is easy to recognize normal character but in cursive character we have to find out the boundary of a character that’s why we have to apply better slant and segmentation techniques. A proper feature extraction method can increase the recognition ratio. In this paper, a chain code based feature extraction method is investigated for developing HCCR system. Chain code is working based on 4-neighborhood or 8–neighborhood methods. In this paper, 8–neighborhood method has been implemented which allows generation of eight different codes for each character. After feature extraction method, Classification techniques have been used for training and testing of Neural Network and other classifier.