Identification of Handwritten Digit Using Deep Learning

The realms of deep learning and machine learning algorithms has resulted in a significant dependence on automated systems for a wide range of tasks, from adding sound to silent films to classifying objects in photographs. With so many possible uses, handwritten text recognition [1] becomes an important field for study. Often called Handwriting Recognition (HWR) or Handwritten Text Recognition (HTR), it involves enabling computers to interpret to read and understand handwritten input from a variety of sources, such as pictures, touch screens, paper documents, and other devices. This is a survey paper focusing on the task of recognizing handwritten digits. This paper focuses on the task of recognizing Handwritten digits using MNIST dataset, employing Support Vector Machines - SVM, Multi-Layer Perceptron-MLP, and CNN models. The primary objective here is to compare the accuracy of these models and evaluate their execution times. The aim is to identify the most effective model for accurately recognizing handwritten digits while considering computational efficiency.