• Lokesh Rathore
• Dr. Ramji Yadav

The identification of handwritten digits has become a significant research challenge in the field of artificial intelligence. Recognizing handwritten digits involves understanding variations in writing styles, where digits may differ in width, size, and orientation. To develop a system that can recognize and classify these digits (ranging from 0 to 9), researchers often employ machine learning and deep learning algorithms. This paper focuses on the recognition of handwritten digits using the well-known MNIST dataset, consisting of 60,000 samples for training the model and 10,000 samples for testing. This paper conducts a comparative analysis of various algorithms, including k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Artificial Neural Network (ANN) and a deep learning algorithm known as Convolutional Neural Network (CNN). The aim is to determine the most efficient technique for precise digit categorisation. As a result, Convolutional Neural Network (CNN) achieved the highest accuracy at 98.79%, making it the best choice for handwritten digit recognition.

MNIST,KNN,SVM,ANN,CNN.

"Handwritten Digit Recognition: Comparative Analysis of Machine Learning and Deep Learning Algorithms on the MNIST Dataset ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 8, page no.42-47, August-2025, Available :http://www.jetir.org/papers/JETIRHA06008.pdf

"Handwritten Digit Recognition: Comparative Analysis of Machine Learning and Deep Learning Algorithms on the MNIST Dataset ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 8, page no. pp42-47, August-2025, Available at : http://www.jetir.org/papers/JETIRHA06008.pdf