Abstract
Abstract An Optical Character Recognition (OCR) approach for handwritten Indian digit is presented in this paper, by using the proposed sector approach. In this approach, the normalized and thinned digit image is divided into sectors with each sector covering a fixed angle. The features totaling 24 include vector distances, angles. For recognition, the K-Nearest-Neighbours classifier is used. This method was tested using 45 patterns for each digit with different writers. The sample images were divided into 20 training and 25 test images. Images in the test set did not appear in the training sets. This method performs extremely well with recognition rates 82.8%. This is a very good performance.
