BeHGAN: Bengali Handwritten Word Generation from Plain Text Using Generative Adversarial Networks

TL;DR

This paper introduces BeHGAN, a generative adversarial network model designed to produce diverse Bengali handwritten words from plain text, addressing the scarcity of datasets and advancing Bengali handwriting synthesis.

Contribution

The paper presents a novel GAN-based method for Bengali handwritten word generation and introduces a new dataset with samples from 500 individuals.

Findings

Successfully generated diverse Bengali handwritten words

Demonstrated the model's ability to produce realistic handwriting

Contributed a new dataset for Bengali handwriting research

Abstract

Handwritten Text Recognition (HTR) is a well-established research area. In contrast, Handwritten Text Generation (HTG) is an emerging field with significant potential. This task is challenging due to the variation in individual handwriting styles. A large and diverse dataset is required to generate realistic handwritten text. However, such datasets are difficult to collect and are not readily available. Bengali is the fifth most spoken language in the world. While several studies exist for languages such as English and Arabic, Bengali handwritten text generation has received little attention. To address this gap, we propose a method for generating Bengali handwritten words. We developed and used a self-collected dataset of Bengali handwriting samples. The dataset includes contributions from approximately five hundred individuals across different ages and genders. All images were pre-processed to ensure consistency and quality. Our approach demonstrates the ability to produce diverse handwritten outputs from input plain text. We believe this work contributes to the advancement of Bengali handwriting generation and can support further research in this area.