CNN-Based Image Classification for Handwritten Digit Recognition
Keywords:
Handwritten digit recognition, CNN, MNIST dataset, image classificationAbstract
In the digital era, handwritten digit recognition (HDR) plays a pivotal role in converting analog information into a digital format. Traditional methods of digitizing handwritten content often come with substantial costs. This essay addresses the issue at hand by putting forth a very effective algorithm designed to accurately recognize handwritten digits from scanned images, thereby significantly reducing expenses. The study focuses on investigating and comparing the way different algorithms perform when categorizing handwritten numbers. The comparison is predicated on varying the number of hidden layers, using various epoch counts, and assessing accuracy. For the experiment, the popular Modified National Institute MNIST (Measurement, Technology, and Standards) dataset for assessment. The results of this study offer insightful information on improving HDR techniques to make handwritten information digitization easier and more affordable. In this study, a systematic exploration of HDR algorithms was conducted, varying key factors such as hidden layers and epochs. The algorithms accuracy in classifying handwritten digits from scanned images was thoroughly evaluated. Leveraging the Comprehensive Modified Nation Institute of Standards and Technology (MNIST) dataset, the research results offer detailed comparative analyses, revealing optimal configurations for HDR algorithms. These findings pave the way for significant advancements in the field, enabling industries reliant on digital conversion to adopt cost-effective, accurate, and efficient HDR methods for processing handwritten information.
Downloads
References
Cireşan, D., Meier, U., Masci, J., & Schmidhuber, J., 2012. Multi-column deep neural networks for image classification. In 2012 IEEE conference on computer vision and pattern recognition (pp. 3642-3649).
Deng, L., Yu, D., & Platt, J. C., 2013. Scalable stacking and learning for building deep architectures. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 2134-2138). IEEE.
Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y., 2016. Deep learning. MIT press Cambridge, 770.
Krizhevsky, A., Sutskever, I., & Hinton, G. E., 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P., 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
Liao, Q., & Poggio, T., 2016. Bridging the gaps between residual learning, recurrent neural networks and visual cortex. arXiv preprint arXiv:1604.03640.
Simard, P. Y., Steinkraus, D., & Platt, J. C., 2003. Best practices for convolutional neural networks applied to visual document analysis. In Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. (Vol. 2, pp. 958-962). IEEE.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R., 2014. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929-1958.
Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K., 2017. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1492-1500).
Downloads
Published
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.