HAND WRITTEN DIGIT RECOGNITION SYSTEM

Abstract

The reliance of humans over machines has never been so high such that from object classification in photographs to adding sound to silent movies everything can be performed with the help of deep learning and machine learning algorithms. Likewise, Handwritten Digit recognition is one of the significant areas of research and development with a streaming number of possibilities that could be attained. Handwritten Number Recognition (HNR), also known as Handwritten Digit Recognition (HDR), is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other devices.We have performed Handwritten Digit Recognition on MNIST Dataset. MNIST data set is a dataset of handwritten images of numbers from 0 to 9. It has 70,000 images of numbers form 0 to 9. In this data set the 60,000 images are used for training and 10,000 for testing. Here we are using Machine Learning and in that we are using an classification algorithm i.e., Logistic Regression.