Handwritten Odia Digits Recognition Using Residual Neural Network

Main Article Content

MrinmoySen, Shaon Bandyopadhyay, Palash Ray, Mahuya Sasmal, Rajesh Mukherjee

Abstract

Handwritten digit recognition is a highly evolved research domain of pattern recognition. Handwritten digits are segmented first and then they are classified using the handwritten digit recognition technique. The Odia script is one of the writing systems in Odisha. In this paper, an efficient Handwritten Odia numeral digit recognition using ResNet is proposed. Deep learning is a recent research trend in this field. Architectures like Residual neural Networks (ResNet) are being used for classification. ResNet is an architecture that is computationally expensive and normally used to provide high accuracy in classification problems. The structural design of the network consists of sacks of two convolutional (Conyv2D) layers with Batch Normalization and an activation function called Relu. We
evaluated our scheme on 4970 handwritten samples of Odia numerals from the ISI database and from the experiment we have achieved 99.20% recognition rate.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Article Details

How to Cite
MrinmoySen, Shaon Bandyopadhyay, Palash Ray, Mahuya Sasmal, Rajesh Mukherjee. (2022). Handwritten Odia Digits Recognition Using Residual Neural Network. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 11(1), 567–574. https://doi.org/10.17762/turcomat.v11i1.11882
Section
Research Articles