HANDWRITTEN RECOGNITION BY USING MACHINE LEARNING APPROACH
P Thangamariappan, J. C. Miraclin Joyce Pamila · International Journal of Engineering Applied Sciences and Technology · 2020
Deep learning is the most powerful machine learning technique in current generation.This paper presents the result of handwritten recognition using deep learning.Handwriting is unique to each individual.So the handwriting is differed from one person to another person.Handwritten Recognition can be done in two ways.One is Online Handwritten recognition and another one is Offline Handwritten Recognition.Online Handwritten recognition system, which takes the input at run time and Offline Handwritten Recognition which works on scanned images.Offline handwritten is the hardest to find the handwriting.MNIST data set is used for this handwritten digit recognition process and it has 70000 handwritten digits.Many Machine Learning Algorithms are developed which can be used for this digit classification.This paper performs the analysis of accuracies and performance measures of algorithm Convolutional Neural Networks (CNN).The proposed approach recognizes with overall accuracy is 93%.