Multiple Classifier Combination for Off-line Handwritten Devnagari Character Recognition

TL;DR

This paper introduces a weighted majority voting ensemble of three MLP classifiers using different feature sets for handwritten Devnagari character recognition, achieving over 92% accuracy on a dataset of 4900 samples.

Contribution

It proposes a novel combination method of multiple classifiers with diverse features, improving recognition accuracy over existing approaches.

Findings

Recognition rate of 92.16% with top five choices

Outperforms recent methods in handwritten Devnagari recognition

Uses diverse features for robust classification

Abstract

This work presents the application of weighted majority voting technique for combination of classification decision obtained from three Multi_Layer Perceptron(MLP) based classifiers for Recognition of Handwritten Devnagari characters using three different feature sets. The features used are intersection, shadow feature and chain code histogram features. Shadow features are computed globally for character image while intersection features and chain code histogram features are computed by dividing the character image into different segments. On experimentation with a dataset of 4900 samples the overall recognition rate observed is 92.16% 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.