img
img
img
img
img
Home / all-journals/ /Article

Bangla Handwritten Characters Recognition Using Convolutional Neural Network


Md. Anwar Hossain1*, Mirza A. F. M. Rashidul Hasan2, A. F. M. Zainul Abadin1, and Nafiul Fatta1

1Department of Information and Communication Engineering, Pabna University of Science and Technology, Pabna-6600, Bangladesh; and 2Department of Information and Communication Engineering, University of Rajshahi, Bangladesh.

*Correspondence: manwar.ice@gmail.com (Md. Anwar Hossain, Associate Professor, Department of Information and Communication Engineering, Pabna-6600, Bangladesh).

Powered by Froala Editor


ABSTRACT

In the Bangla language, there are 50 complex-shaped characters and working with this huge amount of characters with an appropriate set of features is a tough problem to recognize handwritten characters. Moreover, ambiguity and precision errors are common in handwritten words. Furthermore, among a large number of complex-shaped letters, some are quite similar in shape, making handwritten Bangla characters difficult to recognize. In this work, we proposed a convolutional neural network-based approach for recognizing the handwritten Bangla alphabet. In character recognition, the convolutional neural network (CNN) outperforms most of the other models. However, to guarantee a satisfactory performance, CNNs usually need a great number of samples. Bangla handwriting recognition has been a hot topic for several years, but due to the similarity of many Bangla characters, it's difficult to achieve good results. By training and testing on Bangla character datasets, the model gets a 90.22% validation accuracy for Bangalekha isolated dataset and 93.22% validation accuracy for the Ekush dataset. 

Keywords: Deep Learning, Image Recognition, Convolutional Networks, and Handwritten character recognition.

Citation: Hossain MA, Hasan MAFMR, Abadin AFMZ, and  Fatta N. (2022). Bangla handwritten characters recognition using convolutional neural network. Aust. J. Eng. Innov. Technol., 4(2), 27-31. 

https://doi.org/10.34104/ajeit.022.027031


Powered by Froala Editor