Word level Script Identification from Bangla and Devanagri Handwritten Texts mixed with Roman Script

TL;DR

This paper introduces a system for automatically identifying and separating handwritten Bangla, Devanagri, and Roman scripts in mixed-language documents using feature-based classification, achieving over 98% accuracy.

Contribution

It presents a novel script separation method combining script-independent text line extraction with a multi-layer perceptron classifier trained on holistic features.

Findings

Achieved 99.29% accuracy for Bangla-Roman script separation.

Achieved 98.43% accuracy for Devanagri-Roman script separation.

Demonstrated effectiveness on two distinct datasets.

Abstract

India is a multi-lingual country where Roman script is often used alongside different Indic scripts in a text document. To develop a script specific handwritten Optical Character Recognition (OCR) system, it is therefore necessary to identify the scripts of handwritten text correctly. In this paper, we present a system, which automatically separates the scripts of handwritten words from a document, written in Bangla or Devanagri mixed with Roman scripts. In this script separation technique, we first, extract the text lines and words from document pages using a script independent Neighboring Component Analysis technique. Then we have designed a Multi Layer Perceptron (MLP) based classifier for script separation, trained with 8 different wordlevel holistic features. Two equal sized datasets, one with Bangla and Roman scripts and the other with Devanagri and Roman scripts, are prepared for the system evaluation. On respective independent text samples, word-level script identification accuracies of 99.29% and 98.43% are achieved.