Combining Multiple Feature Extraction Techniques for Handwritten Devnagari Character Recognition

TL;DR

This paper presents a handwritten Devnagari character recognition system that combines four feature extraction techniques with neural classifiers, achieving a recognition accuracy of 92.80% on a dataset of 4900 samples.

Contribution

It introduces a novel combination of multiple feature extraction methods and a weighted voting scheme for improved handwritten Devnagari character recognition.

Findings

Achieved 92.80% recognition accuracy on 4900 samples.

Outperformed recent methods in handwritten Devnagari recognition.

Effective integration of diverse features enhances classification success.

Abstract

In this paper we present an OCR for Handwritten Devnagari Characters. Basic symbols are recognized by neural classifier. We have used four feature extraction techniques namely, intersection, shadow feature, chain code histogram and straight line fitting features. Shadow features are computed globally for character image while intersection features, chain code histogram features and line fitting features are computed by dividing the character image into different segments. Weighted majority voting technique is used for combining the classification decision obtained from four Multi Layer Perceptron(MLP) based classifier. On experimentation with a dataset of 4900 samples the overall recognition rate observed is 92.80% as we considered top five choices results. This method is compared with other recent methods for Handwritten Devnagari Character Recognition and it has been observed that this approach has better success rate than other methods.