Improved Handwritten Digit Recognition method using Deep Learning Algorithm

Abstract

One of the essential problems in Computer Vision is identification and classification of important objects. While exhaustive work done on image processing for computation and accuracy performance it is still limited by ambiguity. In current work we compared traditional machine learning method versus Deep Learning model, namely Convolutional Neural Network(CNN), on Handwritten Digit Recognition using MNIST dataset. We showed that CNN algorithm reaches higher recognition accuracy than Support Vector Machine(SVM).