(Received: 2017-06-24, Revised: 2017-09-24 , Accepted: 2017-10-31)
Khaled S. Younis,
The automatic analysis and recognition of offline Arabic handwritten characters from images is an important problem in many applications. Even with the great progress of recent research in optical character recognition, a few problems still wait to be solved, especially for Arabic characters. The emergence of Deep Neural Networks promises a strong solution to some of these problems. We present a deep neural network for the handwritten Arabic character recognition problem that uses convolutional neural network (CNN) models with regularization parameters such as batch normalization to prevent overfitting. We applied the Deep CNN for the AIA9k and the AHCD databases and the classification accuracies for the two datasets were 94.8% and 97.6%, respectively. A study of the network performance on the EMNIST and a form-based AHCD dataset were performed to aid in the analysis.

[1] R. Plamondon and S. N. Srihari, "On-line and Off-line Handwriting Recognition: A Comprehensive Survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 2, no. 1, pp. 63-84, 2000.

[2] A. Belaïd and N. Ouwayed, Segmentation of Ancient Arabic Documents, in "Guide to OCR for Arabic Scripts," Eds. Volker Märgner and Haikal El Abed, Springer-Verlag, London, pp. 103-122, 2011.

[3] G. Abandah, M. Khedher and K. Younis, "Handwritten Arabic Character Recognition Using Multiple Classifiers based on Letter Form," Proceedings of the 5th IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA 2008), pp. 128-133, Innsbruck, Austria, 13-15 Feb. 2008.

[4] G. Abandah, M. Khedher and K. Younis, "Evaluating and Selecting Features for Recognizing Handwritten Arabic Characters," Tech. Report, Computer Eng. Dept., The Univ. of Jordan, Sep. 2007. 

[5] G. Hu, Y. Yang, D. Yi, J. Kittler, W. Christmas, S. Li and T. Hospedales, "When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition," Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 142–150, Santiago, Chile, 13–16 December 2015.

[6] H. Cecotti, "Hierarchical K-nearest Neighbor with GPUs and a High-performance Cluster: Application to Handwritten Character Recognition," International Journal of Pattern Recognition and Artificial Intelligence, vol. 31, no. 2, pp. 1–24, 2017.

[7] M. Abadi et al. "Tensorflow: Large-scale Machine Learning on Heterogeneous Distributed Systems," arXiv preprint arXiv:1603.04467, 2016.

[8] F. Chollet and Keras, GitHub Repository,[Online], Available:, GitHub, 2015.

[9] M. Elleuch, N. Tagougui and M. Kherallah, "Arabic Handwritten Characters Recognition Using Deep Belief Neural Networks," Proc. of the 12th International Multi-Conference on Systems, Signals & Devices (SSD15), pp. 1-5, Mahdia, Tunisia, 16-19 March 2015.

[10] H. Alwzwazy et al., "Handwritten Digit Recognition Using Convolutional Neural Networks," International Journal of Innovative Research in Computer and Communication, vol. 4, no. 2, 2016.

[11] A. Lawgali, "A Survey on Arabic Character Recognition, " International Journal of Signal Processing, Image Processing and Pattern Recognition, vol. 8, no. 2, pp. 401-426, 2015.

[12] J. Al Abodi and X. Li, "An Effective Approach to Offline Arabic Handwriting Recognition," Pattern Analysis and Applications, vol. 40, no. 6, pp. 1883-1901, 2014.

[13] M. Torki et al., "Window-based Descriptors for Arabic Handwritten Alphabet Recognition: A Comparative Study on a Novel Dataset," arXiv preprint arXiv:1411.3519, 2014.

[14] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), vol. 1, pp. 886-893, 2005.

[15] H. Bay, A. Ess, T. Tuytelaars and L. van Gool, "Surf: Speeded-up Robust Features," Journal of Computer Vision and Image Understanding, vol. 110, no. 3, pp. 346-359, 2008.

[16] D. Lowe, "Distinctive Image Features F-ROM Scale-invariant Key Points," International Journal of Computer Vision, vol. 60, pp. 91–110, 2004.

[17] A. Lawgali et al., "HACDB: Handwritten Arabic Characters’ Database for Automatic Character Recognition," European Workshop on Visual Information Processing (EUVIP), pp. 255-259, 2013.

[18] M. Elleuch et al., "Optimization of DBN using Regularization Methods Applied for Recognizing Arabic Handwritten Script," International Conference on Computational Science (ICCS 2017), vol. 108, pp. 2292-2297, Zurich, 12-14 June 2017.

[19] A. El-Sawy, M. Loey and H. El-Bakry, "Arabic Handwritten Characters Recognition Using Convolutional Neural Network," WSEAS Transactions on Computer Research, vol. 5, pp. 11-19, 2017.

[20] G. Fink, "1st International Workshop on Arabic Script Analysis and Recognition (ASAR 2017),"[Online], Available:, Nancy, France, April 3-5, 2017.

[21] I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, pp. 335-339,[Online], Available:

[22] S. Loffe and C. Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," [Online], Available:, 2015.

[23] Dan C. Cire┼čan et al., "Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs," arXiv preprint arXiv:1103.4487, 2011.

[24] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based Learning Applied to Document Recognition," Proceedings of IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.

[25] P. Golik, P. Doetsch and H. Ney, "Cross-entropy vs. Squared Error Training: A Theoretical and Experimental Comparison," Interspeech, vol. 13, 2013.

[26] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, "Dropout: A Simple Way to Prevent Neural Networks from Overfitting," Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014. 

[27] D. P. Kingma and B. Adam, "A Method for Stochastic Optimization," [Online], Available:

[28] M. Pechwitz, S. S. Maddouri, V. Mrgner, N. Ellouze and H. Amiri, "Ifn/enit - database of Handwritten Arabic Words," Colloque Inter. Francophone sur lEcrit et le Document (CIFED), pp. 129–136, 2002.

[29] Y. Le Cun, K. Kavukvuoglu and C. Farabet, "Convolutional Networks and Applications in Vision," Proc. of the IEEE International Symposium on Circuits and Systems (ISCAS'10), Paris, France, 2010.

[30] K. Younis and A. Alkhateeb, "A New Implementation of Deep Neural Networks for Optical Character Recognition and Face Recognition," Proc. of the New Trends in Information Technology (NTIT-2017), The University of Jordan, 25-27 April 2017.

[31] Ke Zhang, "Residual Networks of Residual Networks: Multilevel Residual Networks," IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Latex Class Files, vol. 14, no. 8, Aug. 2016.

[32] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016.

[33] C. Boufenar, M. Batouche and M. Schoenauer, "An Artificial Immune System for Offline Isolated Handwritten Arabic Character Recognition. Evolving Systems," Springer-Verlag, pp.1-17, 2016.

[34] V. Nair and G. Hinton, "Rectified Linear Units Improve Restricted Boltzmann Machines," Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814, Haifa, June 2010.

[35] J. Springenberg, A. Dosovitskiy, T. Brox and M. Riedmiller, "Striving for Simplicity: The All Convolutional Net," arXiv preprint arXiv:1412.6806, 2014.

[36] A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Advances in Neural Information Processing Systems (NIPS), pp. 1097-1105, 2012.

[37] I. Ahmad and G. Fink, "Class-based Contextual Modeling for Handwritten Arabic Text Recognition," International Conference on Frontiers in Handwritten Recognition (ICFHR), pp. 554-559, 2016.

[38] S. Hochreiter and J. Schmidhuber, "Long Short-term Memory," Journal of Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.

[39] B. Balci, D. Saadati and D. Shiferaw, "Handwritten Text Recognition Using Deep Learning," CS231n: Convolutional Neural Networks for Visual Recognition, Stanford Uni., Course Project Report, 2017.

[40] G. Cohen, S. Afshar, J. Tapson and A. Van Schaik, "EMNIST: An Extension of MNIST to Handwritten Letters," arXiv:1702.05373v2, 1 March 2017.

[41] A. Ray, S. Rajeswar and S. Chaudhury, "Text Recognition Using Deep BLSTM Networks," Proc. of the 8th International Conference on Advances in Pattern Recognition (ICAPR), pp. 1-6, Kolkata, India, 4-7 Jan. 2015.