Handwritten Digit Recognition using CNN

Abstract

Handwritten digit recognition allows the computer to recognize the digits written by humans. In general, it is a hard task for the computers to recognize the digits because the handwriting varies with the person and there is no standard handwriting. In some languages the letters overlap making the computer hard to recognize the characters. So, Using Handwritten digit recognition technique we train the machine with different handwritten digits making the computer task easy. In this project a Convolutional Neural Network model was built. Inorder to train the model MNIST dataset is used as it consists of 60,000 training datasets. A graphical user interface is created which captures the image placed in front of the camera and passes the image as the input to the model so that the model predicts the output and the output is displayed in the result section of the graphical user interface.