Support Vector Machine based Handwritten Letters and Digits Recognition using Deep Learning

Abstract

Number recognition can be an important and necessary challenge because handwritten numbers are not similar in size, thickness, position and direction; this method should consider different difficulties to deal with the difficulty of recognizing written numbers. Individuality and assortment in the composition of varieties of different people additionally affect the instance and availability of numbers. It is a process for selecting and composing translated numbers. It's a wide variety of apps, such as programmed arrays, contact points and income related documents, and then beyond. The objective of this work is to implement an algorithmic classification rule for recognizing written numbers. Sometime consequences are probably used various machine learning algorithms like K-means nereast neural networks (KNN), Support vector machine (SVM), KNN and Deep Learning calculations using keras, tensorflow and CNN classifier. The simulation accuracy is 98.70% obtained using CNN and compared with SVM 97%, KNN is 96% and keras as 96%.