Spatial Domain Feature Extraction Methods for Unconstrained Handwritten Malayalam Character Recognition

TL;DR

This paper explores spatial domain feature extraction techniques for recognizing unconstrained handwritten Malayalam characters, employing classifiers like k-NN, SVM, and ELM to improve recognition accuracy.

Contribution

It introduces specific spatial domain features tailored for Malayalam script and evaluates their effectiveness with multiple classifiers.

Findings

Spatial features improve recognition accuracy.

SVM outperforms k-NN and ELM in classification.

Effective recognition of complex Malayalam characters.

Abstract

Handwritten character recognition is an active research challenge,especially for Indian scripts. This paper deals with handwritten Malayalam, with a complete set of basic characters, vowel and consonant signs and compound characters that may be present in the script. Spatial domain features suitable for recognition are chosen in this work. For classification, k-NN, SVM and ELM are employed