A Framework for On-Line Devanagari Handwritten Character Recognition

TL;DR

This paper introduces a stroke-based framework for on-line Devanagari handwritten character recognition, inspired by speech processing, improving accuracy by noise removal and fuzzy directional features.

Contribution

It proposes a novel stroke-based recognition framework applicable to any language, emphasizing primitive recognition and noise handling for improved accuracy.

Findings

Recognition of 69 primitives simplifies character recognition.

Fuzzy directional features enhance stroke recognition accuracy.

Noise removal significantly improves recognition performance.

Abstract

The main challenge in on-line handwritten character recognition in Indian lan- guage is the large size of the character set, larger similarity between different characters in the script and the huge variation in writing style. In this paper we propose a framework for on-line handwitten script recognition taking cues from speech signal processing literature. The framework is based on identify- ing strokes, which in turn lead to recognition of handwritten on-line characters rather that the conventional character identification. Though the framework is described for Devanagari script, the framework is general and can be applied to any language. The proposed platform consists of pre-processing, feature extraction, recog- nition and post processing like the conventional character recognition but ap- plied to strokes. The on-line Devanagari character recognition reduces to one of recognizing one of 69 primitives and recognition of a character is performed by recognizing a sequence of such primitives. We further show the impact of noise removal on on-line raw data which is usually noisy. The use of Fuzzy Direc- tional Features to enhance the accuracy of stroke recognition is also described. The recognition results are compared with commonly used directional features in literature using several classifiers.