CNN Based Handwritten Devanagari Digits Recognition

Authors

  • Kumar G Dept. of Computer Science and Engineering, NIT, Warangal, India
  • Kumar S Computer Science & Engineering, MIT AOE, Pune, India

DOI:

https://doi.org/10.26438/ijcse/v5i7.7174

Keywords:

Devanagri Digits, CNN, SVM, KNN, CUDA, GPU, Tensorflow

Abstract

Handwritten Digit Recognition has huge demand in commercial, administrative and academic domains. In recent years lot of good work has been done to improve accuracy of Handwritten Digit Recognition System but accuracy of such systems depend on large datasets. Deep Convolutional Neural Network have shown superior results to traditional shallow net-works in many recognition task. In this paper, a convolutional neural network (CNN) based Devanagari digit recognition system is highlighted. The dataset contains 21969 hand written 28x28 size images. The result of proposed system showed 99.07% accuracy on our dataset.

References

N. Matic, I. Guyon, J. Denker and V. Vapnik, "Writer-adaptation for on-line handwritten character recognition," Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on, Tsukuba Science City, 1993, pp. 187-191.

C. Wu, W. Fan, Y. He, J. Sun and S. Naoi, "Handwritten Character Recognition by Alternately Trained Relaxation Convolutional Neural Network," 2014 14th International Conference on Frontiers in Handwriting Recognition, Heraklion, 2014, pp. 291-296.

Sreedharamurthy S K and H.R.Sudarshana Reddy, "Feature Subset Selection Using Genetic Algorithms for Handwritten Kannada Alphabets Recognition", International Journal of Computer Sciences and Engineering, Vol.3, Issue.6, pp.94-99, 201

Loc Thanh Huynh, Hung Thang Phung andToai QuangTon, "Using Convolutional Neural Network to Recognize Handwritten Digits", International Journal of Computer Sciences and Engineering, Vol.3, Issue.5, pp.203-206, 2015.

S.U. Bohra, P.V. Ingole , "Review on Neural Network Based Approach Towards English Handwritten Alphanumeric Characters Recognition", International Journal of Computer Sciences and Engineering, Vol.1, Issue.3, pp.22-25, 2013.

Mohd. Aquib Ansari, Diksha Kurchaniya, Manish Dixit, Punit Kumar Johari, "An Effective Approach to an Image Retrieval using SVM Classifier", International Journal of Computer Sciences and Engineering, Vol.5, Issue.6, pp.62-72, 2017.

S. Lee, S. J. Son, J. Oh and N. Kwak, "Handwritten Music Symbol Classification Using Deep Convolutional Neural Networks," 2016 International Conference on Information Science and Security (ICISS), Pattaya, 2016, pp. 1-5.

A. Mowlaei and K. Faez, "Recognition of isolated handwritten Persian/Arabic characters and numerals using support vector machines," 2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718), 2003, pp. 547-554.

A. M. S. Chowdhury and M. S. Rahman, "Towards optimal convolutional neural network parameters for bengali handwritten numerals recognition," 2016 19th International Conference on Computer and Information Technology (ICCIT), Dhaka, 2016, pp. 431-436.

Downloads

Published

2025-11-11
CITATION
DOI: 10.26438/ijcse/v5i7.7174
Published: 2025-11-11

How to Cite

[1]
G. Kumar and S. Kumar, “CNN Based Handwritten Devanagari Digits Recognition”, Int. J. Comp. Sci. Eng., vol. 5, no. 7, pp. 71–74, Nov. 2025.

Issue

Vol. 5 No. 7 (2017): IJCSE July Edition

Section

Review Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.