Arabic Handwritten Digit Recognition using Convolutional Neural Network

Abstract

Arabic is the most widely used language in the world, especially the Arab League Country. Of course, in those countries often use Arabic numeral in banks and business applications, postal zip code and data entry application. This research has focused on handwriting recognition of Arabic numeral that has unlimited variation in human handwriting such as style and shape. The proposed method on the deep learning technique is Convolutional Neural Network. LeNet-5 architect also used in training and recognizing the handwritten image of Arabic numeral as much as 70000 images derived from MADbase dataset. The experimental result on 10000 images of database used is by comparing the number of epoch in training process yields, and the average accuracy is 97.67%.