Handwritten-digit-classification-using-CNN

This can predict handwritten digits from 0 to 9 where data set id directly imported from MNIST. As every person has different style of writing digits humans can recognize easily but for computer it is comparatively a difficult task so here neural network approach is used where in the machine will learn on itself by gaining experiences and the accuracy will increase based upon the experience it gains. The dataset was trained using convolutional neural network algorithm. The overall system accuracy obtained was 83.3%. As human vision is one of the wonders of the world. Humans carry a super computer in head where humans can sense the world or can see the world through evolution of over hundreds and millions of neurons hence handwritten digit recognition isn’t an easy task for machines. Every human has its own way of writing numbers therefore for a machine it becomes difficult to predict digits. Similarly they also have their own tendency of recognizing a digit for example let’s take ‘9’ one can remember it as it has a loop and a stroke thus here in case of machine training set is provided. Here, Neural Network approach is used where several hand written digit examples are given where the system can learn from those examples and predict exactly what the digit is. If the number of training examples is increased accuracy will be further increased.