HANDWRITTEN DIGITS RECOGNITION USING NEURAL NETWORK
AUTHORS:
Mentor
Dr. Rajendra Singh
Affiliation
School of Engineering & Technology Raffles University, Neemrana, India
DOI: 
SHARE THIS ARTICLE
CC BY 4.0 License:
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Abstract
This project focuses on developing a machine learning model to accurately classify handwritten digits (0–9) using image data and presents a robust system for recognizing multi-digit handwritten sequences using a Convolutional Neural Network (CNN) combined with advanced digital image processing. While traditional models focus on single-digit classification, this research addresses the challenge of sequence recognition through spatial segmentation, mass-centering, and morphological dilation. The final system achieves high accuracy by standardizing input handwriting to match the dataset distribution. The MNIST dataset that contains 42,000 rows where each row represents a digit training image and 3,36,000 digit test images of size 28x28 pixels, serves as the primary dataset. The workflow involves data preprocessing steps such as normalization, reshaping, and noise reduction to enhance model performance.
Applications of this system include postal mail sorting, bank check processing, and digitization of handwritten forms. Future scope involves extending the model to multi-digit recognition and deploying it as a real-time web application using Flask or Streamlit.
Applications of this system include postal mail sorting, bank check processing, and digitization of handwritten forms. Future scope involves extending the model to multi-digit recognition and deploying it as a real-time web application using Flask or Streamlit.
Keywords
Machine Learning Deep Learning CNN MNIST Computer Vision Image Classification.
Article Information
PUBLICATION DETAILS
Review Type:
Double-Blind Peer Review
License:
CC BY-NC 4.0
Volume/Issue:
Volume 02, Issue 6
Review Rounds:
2
Article Type:
Research Article
Publication Date:
Jun 06 2026
Article Metrics
Article Views
19
PDF Downloads
0
HOW TO CITE
Copy
Sakshi, , Singh, M. M. & Pooja, (2026). Handwritten Digits Recognition Using Neural Network. International Journal of Science, Strategic Management and Technology, 02(6). https://doi.org/10.55041/ijsmt.v2i6.039
Sakshi, , et al.. "Handwritten Digits Recognition Using Neural Network." International Journal of Science, Strategic Management and Technology, vol. 02, no. 6, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i6.039.
Sakshi, ,Man Singh, and Pooja. "Handwritten Digits Recognition Using Neural Network." International Journal of Science, Strategic Management and Technology 02, no. 6 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i6.039.
References
[1] Nagy G, Nartker TA, Rice SV. Optical character recognition: An illustrated guide to the frontier. InDocument recognition and retrieval VII 1999 Dec 22 (Vol. 3967, pp. 58-69). SPIE.
[2] Torralba A, Efros AA. Unbiased look at dataset bias. InCVPR 2011 2011 Jun 20 (pp. 1521-1528). IEEE.
[3] LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L. Handwritten digit recognition with a back-propagation network. Advances in neural information processing systems. 1989;2.
[4] Lauer F, Suen CY, Bloch G. A trainable feature extractor for handwritten digit recognition. Pattern Recognition. 2007 Jun 1;40(6):1816-24.
[5] Surinta O, Schomaker L, Wiering M. A comparison of feature and pixel-based methods for recognizing handwritten bangla digits. In2013 12th International conference on document analysis and recognition 2013 Aug 25 (pp. 165-169). IEEE.
[6] Chen G, Bui TD. Invariant Fourier-wavelet descriptor for pattern recognition. Pattern recognition. 1999 Jul 1;32(7):1083-8.
[7] Seijas LM, Segura EC. A wavelet-based descriptor for handwritten numeral classification. In2012 International Conference on Frontiers in Handwriting Recognition 2012 Sep 18 (pp. 653-658). IEEE.
[8] Zhang P, Bui TD, Suen CY. Extraction of hybrid complex wavelet features for the verification of handwritten numerals. InNinth International Workshop on Frontiers in Handwriting Recognition 2004 Oct 26 (pp. 347-352). IEEE.
[9] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05) 2005 Jun 20 (Vol. 1, pp. 886-893). Ieee.
[10] Conde C, Moctezuma D, De Diego IM, Cabello E. HoGG: Gabor and HoG-based human detection for surveillance in non-controlled environments. Neurocomputing. 2013 Jan 16;100:19-30.
[2] Torralba A, Efros AA. Unbiased look at dataset bias. InCVPR 2011 2011 Jun 20 (pp. 1521-1528). IEEE.
[3] LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L. Handwritten digit recognition with a back-propagation network. Advances in neural information processing systems. 1989;2.
[4] Lauer F, Suen CY, Bloch G. A trainable feature extractor for handwritten digit recognition. Pattern Recognition. 2007 Jun 1;40(6):1816-24.
[5] Surinta O, Schomaker L, Wiering M. A comparison of feature and pixel-based methods for recognizing handwritten bangla digits. In2013 12th International conference on document analysis and recognition 2013 Aug 25 (pp. 165-169). IEEE.
[6] Chen G, Bui TD. Invariant Fourier-wavelet descriptor for pattern recognition. Pattern recognition. 1999 Jul 1;32(7):1083-8.
[7] Seijas LM, Segura EC. A wavelet-based descriptor for handwritten numeral classification. In2012 International Conference on Frontiers in Handwriting Recognition 2012 Sep 18 (pp. 653-658). IEEE.
[8] Zhang P, Bui TD, Suen CY. Extraction of hybrid complex wavelet features for the verification of handwritten numerals. InNinth International Workshop on Frontiers in Handwriting Recognition 2004 Oct 26 (pp. 347-352). IEEE.
[9] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05) 2005 Jun 20 (Vol. 1, pp. 886-893). Ieee.
[10] Conde C, Moctezuma D, De Diego IM, Cabello E. HoGG: Gabor and HoG-based human detection for surveillance in non-controlled environments. Neurocomputing. 2013 Jan 16;100:19-30.
Ethics and Compliance
✓ All ethical standards met
This article has undergone plagiarism screening and double-blind peer review. Editorial policies have been followed. Authors retain copyright under CC BY-NC 4.0 license. The research complies with ethical standards and institutional guidelines.
Indexed In
Similar Articles
Design Engineering for Smart Document Understanding
(2026)
DOI: 10.55041/ijsmt.v2i3.041
Identifying Nutrition Deficiency in Paddy Leaf using Neural Network
(2026)
DOI: 10.55041/ijsmt.v2i5.099
A Study on Digital Banking and Its Challenges in Rural Areas
(2026)
DOI: 10.55041/ijsmt.v2i3.047
Previous Article
