Handwritten Bangla Digit Recognition Using Deep Learning

TL;DR

This paper presents a deep learning approach for handwritten Bangla digit recognition, achieving high accuracy by combining CNNs with Gabor features and dropout, outperforming existing methods.

Contribution

The study introduces a novel deep neural network framework incorporating Gabor filters and dropout for improved Bangla digit recognition.

Findings

Achieved 98.78% recognition accuracy.

Outperformed existing state-of-the-art algorithms.

Demonstrated effectiveness of Gabor features with CNNs.

Abstract

In spite of the advances in pattern recognition technology, Handwritten Bangla Character Recognition (HBCR) (such as alpha-numeric and special characters) remains largely unsolved due to the presence of many perplexing characters and excessive cursive in Bangla handwriting. Even the best existing recognizers do not lead to satisfactory performance for practical applications. To improve the performance of Handwritten Bangla Digit Recognition (HBDR), we herein present a new approach based on deep neural networks which have recently shown excellent performance in many pattern recognition and machine learning applications, but has not been throughly attempted for HBDR. We introduce Bangla digit recognition techniques based on Deep Belief Network (DBN), Convolutional Neural Networks (CNN), CNN with dropout, CNN with dropout and Gaussian filters, and CNN with dropout and Gabor filters. These networks have the advantage of extracting and using feature information, improving the recognition of two dimensional shapes with a high degree of invariance to translation, scaling and other pattern distortions. We systematically evaluated the performance of our method on publicly available Bangla numeral image database named CMATERdb 3.1.1. From experiments, we achieved 98.78% recognition rate using the proposed method: CNN with Gabor features and dropout, which outperforms the state-of-the-art algorithms for HDBR.