Design and Development of Handwritten Digit Recognition System Using Machine Learning

Abstract

In any system ,the wide range of writing styles, handwritten digit recognition has proven to be a challenging task.The wide variety of writing styles has made it challenging to read handwritten numerals.. Numerous research have demonstrated the superior performance of neural networks in the classification of data. The major goal of this work is to compare various existing classification models in order to give effective and trustworthy methods for handwritten numeral recognition. As training sets, a total of 45,000 images with a pixel size of 2828 were employed. The original image was compared to the training sets and images. We also found that the classifier's accuracy increases with the amount of training data. The study's conclusion shows that K-NN maintains an accuracy of 96.7% as opposed to 96.8% while processing data at a rate nearly ten times faster than a neural network.