Recognition of Non-Compound Handwritten Devnagari Characters using a Combination of MLP and Minimum Edit Distance

TL;DR

This paper presents a two-stage offline handwritten Devnagari character recognition method combining neural networks and minimum edit distance, achieving over 90% accuracy on a large dataset.

Contribution

It introduces a hybrid recognition approach that uses MLP classifiers for distinct characters and minimum edit distance for similar shapes, improving accuracy.

Findings

Overall recognition accuracy of 90.74%.

Effective combination of neural networks and edit distance techniques.

Utilization of corner detection for shape analysis.

Abstract

This paper deals with a new method for recognition of offline Handwritten non-compound Devnagari Characters in two stages. It uses two well known and established pattern recognition techniques: one using neural networks and the other one using minimum edit distance. Each of these techniques is applied on different sets of characters for recognition. In the first stage, two sets of features are computed and two classifiers are applied to get higher recognition accuracy. Two MLP's are used separately to recognize the characters. For one of the MLP's the characters are represented with their shadow features and for the other chain code histogram feature is used. The decision of both MLP's is combined using weighted majority scheme. Top three results produced by combined MLP's in the first stage are used to calculate the relative difference values. In the second stage, based on these relative differences character set is divided into two. First set consists of the characters with distinct shapes and second set consists of confused characters, which appear very similar in shapes. Characters of distinct shapes of first set are classified using MLP. Confused characters in second set are classified using minimum edit distance method. Method of minimum edit distance makes use of corner detected in a character image using modified Harris corner detection technique. Experiment on this method is carried out on a database of 7154 samples. The overall recognition is found to be 90.74%.