Online Arabic Handwriting Recognition with Dropout Applied in Deep Recurrent Neural Networks

Proceedings - 12th IAPR International Workshop on Document Analysis Systems, DAS 2016

Volumn , Issue , 2016, Pages 417-421

  Maalej, Rania ^a   Tagougui, Najiba ^b,c   Kherallah, Monji ^d  

^a UNIVERSITY OF SFAX   (Tunisia)

^b MIRACL Laboratory   (Tunisia)

^c AL BAHA UNIVERSITY   (Saudi Arabia)

^d UNIVERSITY OF SFAX   (Tunisia)

Author keywords

Deep neural Network; Dropout; Handwriting recognition; Online recognition; Recurrent Neural Network

Indexed keywords

CHARACTER RECOGNITION;

DEEP NEURAL NETWORKS; DROPOUT; HANDWRITING RECOGNITION; INPUT AND OUTPUTS; LARGE VOCABULARY; MOBILE COMPUTERS; ON-LINE RECOGNITION; ONLINE ARABIC HANDWRITING RECOGNITION;

RECURRENT NEURAL NETWORKS;

EID: 84979610014     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/DAS.2016.49     Document Type: Conference Paper

References (24)

1. Boubaker, H., Elbaati, A., Tagougui, N., El Abed, H., Kherallah, M., & Alimi, A. M. (2012). Online Arabic databases and applications. In Guide to OCR for Arabic Scripts (pp. 541-557). Springer London
2. Tagougui, N., Kherallah, M., & Alimi, A. M. (2013). Online Arabic handwriting recognition: a survey. International Journal on Document Analysis and Recognition (IJDAR), 16(3), 209-226
3. Biadsy, F., El-Sana, J., & Habash, N. Y. (2006). Online Arabic handwriting recognition using hidden markov models
4. Tagougui, N., Boubaker, H., Kherallah, M., & Alimi, A. M. (2014). A Hybrid NN/HMM modeling technique for online Arabic handwriting recognition. ArXiv preprint arXiv:1401.0486
5. Graves, A., Liwicki, M., Bunke, H., Schmidhuber, J., & Fernández, S. (2008). Unconstrained on-line handwriting recognition with recurrent neural networks. InAdvances in Neural Information Processing Systems (pp. 577-584)
6. Graves, A., Mohamed, A. R., & Hinton, G. (2013, May). Speech recognition with deep recurrent neural networks. In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on (pp. 6645-6649). IEEE
7. Kozielski, M., Doetsch, P., & Ney, H. (2013, August). Improvements in RWTH's System for Off-Line Handwriting Recognition. In Document Analysis and Recognition (ICDAR), 2013 12th International Conference on (pp. 935-939). IEEE
8. Liwicki, M., Graves, A., Bunke, H., & Schmidhuber, J. (2007, September). A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks. In Proc. 9th Int. Conf. on Document Analysis and Recognition (Vol. 1, pp. 367-371)
9. Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. ArXiv preprint arXiv:1207.0580
10. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929-1958
11. Miao, Y., & Metze, F. (2013). Improving low-resource CD-DNN-HMM using dropout and multilingual DNN training
12. Zhang, S., Bao, Y., Zhou, P., Jiang, H., & Dai, L. (2014, May). Improving deep neural networks for LVCSR using dropout and shrinking structure. In Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on (pp. 6849-6853). IEEE
13. Ognawala, S., & Bayer, J. (2014). Regularizing Recurrent Networks-On Injected Noise and Norm-based Methods. ArXiv preprint arXiv:1410.5684
14. Pham, V., Bluche, T., Kermorvant, C., & Louradour, J. (2014, September). Dropout improves recurrent neural networks for handwriting recognition. InFrontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on (pp. 285-290). IEEE
15. Zaremba, W., Sutskever, I., & Vinyals, O. (2014). Recurrent neural network regularization. ArXiv preprint arXiv:1409.2329
16. El Abed, H., Margner, V., Kherallah, M., & Alimi, A. M. (2009, July). Icdar 2009 online Arabic handwriting recognition competition. In Document Analysis and Recognition, 2009. ICDAR'09. 10th International Conference on (pp. 1388-1392). IEEE
17. El Abed, H., Kherallah, M., Märgner, V., & Alimi, A. M. (2011). Online Arabic handwriting recognition competition. International Journal on Document Analysis and Recognition (IJDAR), 14(1), 15-23
18. Kherallah, M., Tagougui, N., Alimi, A. M., Abed, H. E., & Märgner, V. (2011, September). Online Arabic handwriting recognition competition. In Document Analysis and Recognition (ICDAR), 2011 International Conference on (pp. 1454-1458). IEEE
19. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780
20. Graves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006, June). Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd international conference on Machine learning (pp. 369-376). ACM
21. Levenshtein, V. I. (1966, February). Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady (Vol. 10, No. 8, pp. 707-710)
22. Abdou, S., Fahmy, A., Hosney, I., & Mostafa, I. (2009, April). Artificial Tutor For Arabic Handwriting Training. In Proceedings of the Second International Conference on Arabic Language Resources and Tools (pp. 24-30)
23. Abdelazeem, S., & Eraqi, H. M. (2011, September). On-line Arabic handwritten personal names recognition system based on HMM. In Document Analysis and Recognition (ICDAR), 2011 International Conference on (pp. 1304-1308). IEEE
24. Graves, A. (2008). Rnnlib: A recurrent neural network library for sequence learning problems. http://sourceforge.net/projects/rnnl/