Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194957,
        author = {MR P Chaitanya and D Deepika and G Jyothi Sri and K Aditya Ram and G Jeevan Sai Kiran},
        title = {MNIST Digit Classification Deep Learning Approach for Efficient Handwritten Digit Recognition},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8153-8157},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194957},
        abstract = {Handwritten digit recognition is a fundamental problem in computer vision and pattern recognition, with wide applications in postal mail sorting, bank check processing, and form digitization. This paper presents a deep learning approach for efficient classification of handwritten digits using the MNIST dataset, which consists of 70,000 grayscale images of digits (0–9). The study uses data preprocessing techniques such as normalization, reshaping, and data augmentation, followed by the application of Convolutional Neural Network (CNN) architectures for classification. Algorithms such as Logistic Regression, Support Vector Machine (SVM), and deep CNN models are applied for digit classification, and the results show that deep learning can effectively identify handwritten digit patterns and provide highly accurate recognition. The proposed Deep CNN model achieves 99.42% accuracy on the MNIST test set, with further improvement to 99.56% through data augmentation techniques.},
        keywords = {Handwritten Digit Recognition, Deep Learning, CNN, MNIST Dataset, Image Classification},
        month = {March},
        }