Spectral Graph-based Features for Recognition of Handwritten Characters: A Case Study on Handwritten Devanagari Numerals

TL;DR

This paper introduces a spectral graph-based feature extraction method for handwritten Devanagari numerals, effectively capturing writing styles and cursiveness to improve recognition accuracy.

Contribution

It proposes a novel spectral graph embedding approach for representing handwritten characters, addressing limitations of existing feature extraction techniques.

Findings

Demonstrated improved recognition performance on the Devanagari numeral dataset.

Validated the robustness of spectral graph features in capturing handwriting variations.

Showed potential for future applications in handwritten character recognition systems.

Abstract

Interpretation of different writing styles, unconstrained cursiveness and relationship between different primitive parts is an essential and challenging task for recognition of handwritten characters. As feature representation is inadequate, appropriate interpretation/description of handwritten characters seems to be a challenging task. Although existing research in handwritten characters is extensive, it still remains a challenge to get the effective representation of characters in feature space. In this paper, we make an attempt to circumvent these problems by proposing an approach that exploits the robust graph representation and spectral graph embedding concept to characterise and effectively represent handwritten characters, taking into account writing styles, cursiveness and relationships. For corroboration of the efficacy of the proposed method, extensive experiments were carried out on the standard handwritten numeral Computer Vision Pattern Recognition, Unit of Indian Statistical Institute Kolkata dataset. The experimental results demonstrate promising findings, which can be used in future studies.