Author(s)

Tandra Rani Das¹, Sharad Hasan¹, Md. Rafsan Jani¹, Fahima Tabassum², Md. Imdadul Islam¹

¹Department of Computer Science & Engineering, Jahangirnagar University, Savar, Dhaka, Bangladesh.
²Institute of Information Technology, Jahangirnagar University, Savar, Dhaka, Bangladesh.

The necessity of recognizing handwritten characters is increasing day by day because of its various applications. The objective of this paper is to provide a sophisticated, effective and efficient way to recognize and classify Bangla handwritten characters. Here an extended convolutional neural network (CNN) model has been proposed to recognize Bangla handwritten characters. Our CNN model is tested on “BanglalLekha-Isolated” dataset where there are 10 classes for digits, 11 classes for vowels and 39 classes for consonants. Our model shows accuracy of recognition as: 99.50% for Bangla digits, 93.18% for vowels, 90.00% for consonants and 92.25% for combined classes.

Loss and Accuracy, Deep Neural Network, Image Classification, Noise Removal, CNN and HCR

Das, T. , Hasan, S. , Jani, M. , Tabassum, F. and Islam, M. (2021) Bangla Handwritten Character Recognition Using Extended Convolutional Neural Network. Journal of Computer and Communications, 9, 158-171. doi: 10.4236/jcc.2021.93012.