Handwritten Digit Recognition Using Convolutional Neural Networks: A Case Study on the MNIST Dataset
Abstract
The recognition of handwritten digits is a fundamental task in computer vision and pattern recognition. This study focused on classifying handwritten digits (0–9) from the MNIST dataset using a Convolutional Neural Network (CNN). CNNs can automatically identify spatial and hierarchical features within image data. The developed CNN model achieved a test accuracy of 99.27%, surpassing traditional methods such as Support Vector Machines (SVM) and K-nearest neighbors. The results show that deep learning-based feature extraction provides a strong and efficient framework for practical uses like postal automation, bank check processing, and digital document verification.
References
C. M. Bishop, “Pattern Recognition and Machine Learning,” Journal of Electronic Imaging, vol. 16, no. 4, p. 049901, Jan. 2007, doi: 10.1117/1.2819119.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998, doi: 10.1109/5.726791.
Y. LeCun, C. Cortes, and C. J. C. Burges, “The MNIST database of handwritten digits.” [Online]. Available: http://yann.lecun.com/exdb/mnist
D. C. Cireşan, U. Meier, and J. Schmidhuber, “Multi-column deep neural networks for image classification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2012, pp. 3642–3649, doi: 10.1109/CVPR.2012.6248110.
G. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Improving neural networks by preventing co-adaptation of feature detectors,” arXiv preprint arXiv:1207.0580, 2012. [Online]. Available: https://arxiv.org/abs/1207.0580
H. A. Alhamad, M. K. Hasan, and M. A. Al-Qutayri, “Handwritten recognition techniques: A comprehensive review,” Symmetry, vol. 16, no. 4, p. 588, 2024, doi: 10.3390/sym16060588.
V. Agrawal, A. Patil, and R. Waghmare, “Exploration of advancements in handwritten document recognition,” Int. J. Comput. Appl., vol. 187, no. 3, pp. 12–19, 2024, doi: 10.1016/j.iswa.2024.200358.
Refbacks
- There are currently no refbacks.