AUTHORS: Ahmed El-Sawy, Mohamed Loey, Hazem EL-Bakry

Download as PDF

ABSTRACT: Handwritten Arabic character recognition systems face several challenges, including the unlimited variation in human handwriting and large public databases. In this work, we model a deep learning architecture that can be effectively apply to recognizing Arabic handwritten characters. A Convolutional Neural Network (CNN) is a special type of feed-forward multilayer trained in supervised mode. The CNN trained and tested our database that contain 16800 of handwritten Arabic characters. In this paper, the optimization methods implemented to increase the performance of CNN. Common machine learning methods usually apply a combination of feature extractor and trainable classifier. The use of CNN leads to significant improvements across different machine-learning classification algorithms. Our proposed CNN is giving an average 5.1% misclassification error on testing data.

KEYWORDS: Arabic Character Recognition, Deep Learning, Convolutional Neural Network

REFERENCES:

[1] R. Sarkhel, N. Das, A.K. Saha, and M. Nasipuri, A multi-objective approach towards cost effective isolated handwritten Bangla character and digit recognition, Pattern Recognition, 58, 2016, pp. 172-189.

[2] M. Tounsi, I. Moalla, A.M. Alimi, and F. Lebouregois, Arabic characters recognition in natural scenes using sparse coding for feature representations, Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 1036-1040.

[3] D.K. Sahu and C.V. Jawahar, Unsupervised feature learning for optical character recognition, Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 1041-1045.

[4] M.N. Ibrahim, S.N. Bilmas, A. Babiker, and M. Idroas, A Framework of an Online Self-Based Learning for Teaching Arabic as Second Language (TASL), 2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation, 2013, pp. 255-260.

[5] Y. Liang, J. Wang, S. Zhou, Y. Gong, and N. Zheng, Incorporating image priors with deep convolutional neural networks for image superresolution, Neurocomputing,194, 2016, pp. 340- 347.

[6] D.S. Maitra, U. Bhattacharya, and S.K. Parui, CNN based common approach to handwritten character recognition of multiple scripts, Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 1021-1025.

[7] H.C. Shin, H.R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura, and R.M. Summers, Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning, IEEE Transactions on Medical Imaging, 35, 2016, pp. 1285-1298.

[8] J. Bai, Z. Chen, B. Feng, and B. Xu, Image character recognition using deep convolutional neural network learned from different languages, 2014 IEEE International Conference on Image Processing (ICIP), 2014, pp. 2560-2564.

[9] A. Yuan, G. Bai, L. Jiao, and Y. Liu, Of- fline handwritten English character recognition based on convolutional neural network, Document Analysis Systems (DAS), 2012 10th IAPR International Workshop on, 2012, pp. 125-129.

[10] C. Wu, W. Fan, Y. He, J. Sun, and S. Naoi, Handwritten Character Recognition by Alternately Trained Relaxation Convolutional Neural Network, Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on, 2014, pp. 291-296.

[11] Z. Zhong, L. Jin, and Z. Feng, Multi-font printed Chinese character recognition using multipooling convolutional neural network, Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 96- 100.

[12] W. Yang, L. Jin, Z. Xie, and Z. Feng, Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge, Proc. Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 551- 555.

[13] M. He, S. Zhang, H. Mao, and L. Jin, Recognition confidence analysis of handwritten Chinese character with CNN, Proc. Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 61-65.

[14] Z. Zhong, L. Jin, and Z. Xie, High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps, Proc. Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 846-850.

[15] I.-J. Kim, and X. Xie, Handwritten Hangul recognition using deep convolutional neural networks, International Journal on Document Analysis and Recognition (IJDAR), 18, 2015, pp. 1- 3.

[16] R. Anil, K. Manjusha, S.S. Kumar, and K.P. Soman, Convolutional Neural Networks for the Recognition of Malayalam Characters, Proc. Document Analysis and Recognition (ICDAR), 2015 13th International Conference on, 2015, pp. 1041-1045.

[17] S. Acharya, A.K. Pant, and P.K. Gyawali, Deep learning based large scale handwritten Devanagari character recognition, 2015 9th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), 2015, pp. 1-6.

[18] P. Singh, A. Verma, and N.S. Chaudhari, Deep Convolutional Neural Network Classifier for Handwritten Devanagari Character Recognition, Information Systems Design and Intelligent Applications: Proceedings of Third International Conference INDIA ,2 , 2016, pp. 551-561.

[19] S.T. Soman, A. Nandigam, and V.S. Chakravarthy, An efficient multiclassifier system based on convolutional neural network for offline handwritten Telugu character recognition,Proc. Communications (NCC), 2013 National Conference on , 2013, pp. 1-5.

[20] R.S. Hussien, A.A. Elkhidir, and M.G. Elnourani, Optical Character Recognition of Arabic handwritten characters using Neural Network, Proc. Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE), 2015 International Conference on , 2015, pp. 456-461.

[21] A. ElAdel, R. Ejbali, M. Zaied, and C.B. Amar, Dyadic Multi-resolution Analysis-Based Deep Learning for Arabic Handwritten Character Classification, Proc. Tools with Artificial Intelligence (ICTAI), 2015 IEEE 27th International Conference on , 2015, pp. 807-812.

[22] M. Elleuch, N. Tagougui, and M. Kherallah, Arabic handwritten characters recognition using Deep Belief Neural Networks, Proc. Systems, Signals & Devices (SSD), 2015 12th International Multi-Conference on , 2015, pp. 1-5.

[23] M. Shatnawi, and S. Abdallah, Improving Handwritten Arabic Character Recognition by Modeling Human Handwriting Distortions, ACM Trans. Asian Low-Resour. Lang. Inf. Process. , 15, 2015, pp. 1-12.

[24] M. Kef, L. Chergui, and S. Chikhi, A novel fuzzy approach for handwritten Arabic character recognition, Pattern Analysis and Applications, 2015, pp. 1-16.

[25] J. Al Abodi, and X. Li, An effective approach to offline Arabic handwriting recognition, Pattern Analysis and Applications, 40, 2014, pp. 1883- 1901.

[26] A. Lawgali, M. Angelova and A. Bouridane, A Framework for Arabic Handwritten Recognition Based on Segmentation, International Journal of Hybrid Information Technology, 7, 2014, pp. 413-428.

[27] V. Nair, and G.E. Hinton, Rectified Linear Units Improve Restricted Boltzmann Machines, Machine Learning -International Workshop Then Conference, 2010, pp. 807-814.

[28] F. Hussain and J. Je ong, Efficient deep neural network for digital image compression employing rectified linear neurons, Journal of Sensors, 2016, pp. 1-7.

[29] M. Li, T. Zhang, Y. Chen, and A. J. Smola, Effi- cient mini-batch training for stochastic optimization, in Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 14, (New York, NY, USA), 2014, pp. 661-670.

[30] I. Sutskever, J. Martens, G. E. Dahl, and G. E. Hinton, On the importance of initialization and momentum in deep learning, in Proceedings of the 30th International Conference on Machine Learning (ICML-13), vol. 28, 2013, pp. 1139- 1147.