Convolutional Neural Network Model for Arabic Handwritten Characters Recognition

Abstract: In this paper, we presented a Convolutional Neural Network (CNN) model for off-line Arabic handwritten character recognition. The proposed CNN model used the dataset which prepared by Sudan University of Science and Technology- Arabic Language Technology group. The dataset is pre-processed before feeding it to the CNN model. In the pre-processing, all the characters images are size normalized to fit in a 20 by 20 pixel and then centred in a scaled images of size 28×28 pixel using the centre of mass then all the images are converted to be having a black background and white foreground colours. The pre-processed images are fed to the CNN model, which is constructed using the sequential model of the Keras library under tensorflow environment. The accuracy obtained varied from 93.5% as test accuracy to 97.5% as training accuracy showing better results than other methods that used the same dataset.

Keywords: Convolutional Neural Network CNN, Handwritten Characters, Keras, pre-processing