Digitalization has become very prominent in today’s world. The need for storing information in computers is rapidly increasing. Converting handwritten documents into digital form by humans is often difficult and time-consuming. With the rapid development of technology, human’s reliance on machines to do time-consuming and monotonic tasks also greatly increased. Machine learning and deep learning are the major fields in Computer Science that have developed intelligent algorithms to train machines to do a set of repetitive tasks. Handwritten digit recognition is one of the significant areas of research and development with an increasingly large number of possibilities that could be attained. Handwritten Digit Recognition is the ability of a computer to receive and interpret handwritten input from various sources such as paper documents, photographs, touch screens, and other devices. This paper illustrates handwritten digit recognition with the help of MNIST datasets using Support Vector Machines (SVM) and Convolution Neural Network (CNN) models. The main objective of this paper is to compare the accuracy of the models stated above and develop a Graphical User Interface (GUI) application with the most accurate model.