Recognition of Isolated Handwritten Arabic Characters

Abstract

The challenges that face the handwritten Arabic recognition are overwhelming such as different varieties of handwriting and few public databases available. Also, teaching the non-Arabic speaker at the young age is very difficult due to the unfamiliarity of the words and meanings. So, this project is focused on building a model of a deep learning architecture with convolutional neural network (CNN) and multilayer perceptron (MLP) neural network by using python programming language. This project analyzes the performance of a public database which is Arabic Handwritten Characters Dataset (AHCD). However, training this database with CNN model has achieved a test accuracy of 95.27% while training it with MLP model achieved 72.08%. Therefore, the CNN model is suitable to be used in the application device.