Efficient Feature Extraction Techniques for Offline Handwritten Gurmukhi Character Recognition

Abstract

As a result of advances in optical character recognition research, several techniques for handwritten character recognition have surfaced. These techniques require good quality features as their input for the recognition process. In this paper, we have proposed two different feature extraction techniques, namely, parabola curve fitting based features and power curve fitting based features for offline handwritten Gurmukhi character recognition. In order to assess the quality of features in offline handwritten Gurmukhi character recognition, we have also analyzed the performance of other recently proposed feature extraction techniques, namely, zoning, diagonal, directional, transition, intersection and open end points, gradient and chain code features. Each technique has been tested by using 3,500 images of offline handwritten Gurmukhi characters. Support vector machine (SVM) and k-NN classifiers have been used to recognize the characters in this work. The proposed system achieves a recognition accuracy of 98.10 and 97.14 % using k-NN and SVM classifiers, respectively, when power curve fitting based features are used as input to the classification process.