![](http://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2022/10/vector.jpg)
Shreyash Tarade,
![](http://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2022/10/vector.jpg)
Sneha Tanpure,
![](http://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2022/10/vector.jpg)
Sanket Pawar,
![](http://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2022/10/vector.jpg)
Shreeharsh Puntambekar,
- Student, Department of Computer Engineering RDTC’s, Shri Chhatrapati Shivajiraje College of Engineering, Pune, Maharashtra, India
- Student, Department of Computer Engineering RDTC’s, Shri Chhatrapati Shivajiraje College of Engineering, Pune, Maharashtra, India
- Student, Department of Computer Engineering RDTC’s, Shri Chhatrapati Shivajiraje College of Engineering, Pune, Maharashtra, India
- Student, Department of Computer Engineering RDTC’s, Shri Chhatrapati Shivajiraje College of Engineering, Pune, Maharashtra, India
Abstract
Handwritten digit recognition is a fundamental problem in the field of computer vision and machine learning with numerous applications, such as postal code recognition, bank check processing, and digitizing historical documents. Convolutional Neural Networks have demonstrated remarkable success in various image recognition tasks, making them a popular choice for digit recognition. In this study, we present an enhanced approach to handwritten digit recognition using CNNs. Handwritten digit recognition plays a pivotal role in various applications, including optical character recognition, digit based and digitization of historical documents. Our method incorporates several novel techniques and optimizations to achieve superior accuracy and efficiency in digit recognition tasks. We begin by preprocessing the input images to enhance their quality and reduce noise. Subsequently, we employ a deep CNN architecture with multiple convolutional and pooling layers to extract hierarchical features from the digit images. Batch normalization and dropout layers are strategically applied to improve convergence and reduce overfitting. Additionally, we introduce data augmentation methods, such as rotation, scaling, and translation, to improve the model’s generalization capabilities and reduce overfitting.
Keywords: Handwritten digit recognition, Convolutional Neural Network, Enhanced digit recognition, Image recognition, Epochs
[This article belongs to International Journal of VLSI Circuit Design & Technology(ijvcdt)]
Browse Figures
References
- M. Ashikur Rahman et al., “Two Decades of Bengali Handwritten Digit Recognition: A Survey,” in IEEE Access, vol. 10, pp. 92597- 92632, 2022.
- Khatun, M. S. Shahriar, M. H. Hasan, K. Das, S. Ahmed, and M. S. Islam, “A systematic review on the chronological development of Bangla sign language recognition systems,” in Proc. Joint 10th Int. Conf. Informat., Electron. Vis. (ICIEV) 5th Int. Conf. Imag., Vis. Pattern Recognit. (icIVPR), pp. 19, Aug. 2021.
- Assegie, T. A., Nair, P. S., 2019 “Handwritten digits recognition with decision tree classification: a machine learning approach,” International Journal of Electrical and Computer Engineering (IJECE), Indonesia, 446-4451
- Laimeche L., Meraoumia A., Bendjenna H.: (2019), “Enhancing LSB embedding schemes using chaotic maps systems”, In: Neural Computing and Applications, Springer-Verlag Berlin Heidelberg, 2019. Computing and Applications, Springer-Verlag Berlin Heidelberg, 2019
- Savita Ahlawat, Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN), Received: 25 May 2020.
- Abhishek Sachdeva Prerna Mahajan, A Study of Encryption Algorithms AES, DES and RSA for Security. June 2020
- 6].Atheer Sultan Almutiri, Bashaier Alqahtani, Rahaf Mohammed Alamri, Hanan Fahhad Alqahtani, Nada Nasser Alqahtani, Ghadeer Mohammed alshammari, and Azza. A. Ali Dalia Mubarak Alsaffar, Image Encryption Based on AES and RSA Algorithms, March 24, 2020.
- Matthew Y.W. Teow Artificial Intelligence Lab (21 October 2017), “Understanding Convolutional Neural Networks Using A Minimal Model for Handwritten Digit Recognition”, 2017 IEEE 2nd International Conference on Automatic Control and Intelligent Systems (I2CACIS 2017), Kota Kinabalu, Sabah, Malaysia, pp. 167-172.
- Dan ClaudiuCires¸an, Ueli Meier, Luca Maria Gambardella, Jurgen Schmidhuber (March 2010),
- ¨Deep, Big, Simple Neural Nets for Handwritten Digit Recognition”, arXiv, pp. 1-14.
- Li Deng (November 2012), “The MNIST Database of Handwritten Digit Images for Machine Learning Research”, Best of the web series, IEEE signal processing magazine, pp. 141-142.
- Le Cun, L. D. Jackel, B. Boser, J. S. Denker, H. P. Graf, I. Guyon, D. Henderson, R. E. Howard, W. Hub, “Handwritten Digit Recognition: Applications of Neural Network Chips and Automatic Learning” NATO ASI series F: Computer and system sciences, Vol. 68, pp. 41-46
Volume | 02 |
Issue | 01 |
Received | May 13, 2024 |
Accepted | May 23, 2024 |
Published | August 30, 2024 |