Open Access Open Access  Restricted Access Subscription or Fee Access

On-Line Arabic Characters Recognition Using Enhanced Time Delay Neural Networks


(*) Corresponding author


Authors' affiliations


DOI: https://doi.org/10.15866/irecap.v7i4.13204

Abstract


This paper concerns with the online recognition of isolated hand writing Arabic characters, through, the interpretation of a script presented by a pen trajectory. This technique was generally used in the electronic organizers of Personal Digital Assistant type. First of all, we have built a data base with several scripters using a graphic tablet which will be used in our application. In order to have a precise recognition of the isolated characters, it is important to model their structure the most correctly possible. In this work we present the study, the implementation and the result of the test of a particular neural network which is the Time Delay Neural Networks. We have followed a two steps approach, in the first one, the character characteristics are extracted, and in the second one, a temporal multi-layered perception is developed for a future classification. Our temporal approach with the adaptive topology, responds to the nature of the Arabic script during the acquisition phase while the use of different learning algorithms can minimize the cost function and improve recognition rates. The parameterization of these two parts will allow us to analyze the impact of the neural network topology on the results of character recognition rates.
Copyright © 2017 Praise Worthy Prize - All rights reserved.

Keywords


Arabic Characters; On-Line Recognition; Convolution Neural Network; Time Delay Neural Networks

Full Text:

PDF


References


I. Ahmad, « Modeling and training options for handwritten Arabic text recognition », 2016.
http://dx.doi.org/10.1109/icfhr.2016.0107

W. Li et M. A. Renshaw, « Direct Handwriting Editing », 2017.
http://dx.doi.org/10.1109/icfhr.2012.250

D. Keysers, T. Deselaers, H. A. Rowley, L.-L. Wang, et V. Carbune, « Multi-Language Online Handwriting Recognition », IEEE Trans. Pattern Anal. Mach. Intell., 2016.
http://dx.doi.org/10.1109/tpami.2016.2572693

E. Caillault, « Architecture et apprentissage d’un système hybride neuro-markovien pour la reconnaissance de l’écriture manuscrite en-ligne », université de Nantes, 2005.
http://dx.doi.org/10.3845/ree.1997.080

M. Ltaief, H. Bezine, et A. M. Alimi, « A Spiking Neural Network Model for Complex Handwriting Movements Generation », Int. J. Comput. Sci. Inf. Secur., vol. 14, no 7, p. 319, 2016.
http://dx.doi.org/10.1109/icfhr.2016.0094

R. Saabni et J. El-Sana, « Hierarchical on-line arabic handwriting recognition », in Document Analysis and Recognition, 2009. ICDAR’09. 10th International Conference on, 2009, p. 867–871.
http://dx.doi.org/10.1109/icdar.2009.263

O. B. A. Ahmed et others, « Two Stages Neuro-Fuzzy System for Isolated Arabic Handwritten Character Recognition », Sudan University of Science and Technology, 2017.
http://dx.doi.org/10.5121/csit.2014.4219

N. Mezghani, A. Mitiche, et M. Cheriet, « Estimation de densité de probabilité par maximum d’entropie et reconnaissance bayesienne de caractères Arabes en-ligne. », 2006.
http://dx.doi.org/10.1787/888932326166

F. Biadsy, J. El-Sana, et N. Habash, « Online arabic handwriting recognition using hidden markov models », in Tenth International Workshop on Frontiers in Handwriting Recognition, 2006.
http://dx.doi.org/10.1109/acpr.2011.6166664

Y. Chherawala, P. P. Roy, et M. Cheriet, « Combination of context-dependent bidirectional long short-term memory classifiers for robust offline handwriting recognition », Pattern Recognit. Lett., vol. 90, p. 58–64, 2017.
http://dx.doi.org/10.1016/j.patrec.2017.03.012

Y. Nibret et W. Mulugeta, « Online Ethiopic Handwriting Character Recognition System (OEHCRS): a Hybrid Approach using Discrete HMM over Structural Primitives », 2017.
http://dx.doi.org/10.1109/icfhr.2012.213

X.-Y. Zhang, F. Yin, Y.-M. Zhang, C.-L. Liu, et Y. Bengio, « Drawing and recognizing chinese characters with recurrent neural network », IEEE Trans. Pattern Anal. Mach. Intell., 2017.
http://dx.doi.org/10.1109/tpami.2017.2695539

I. Abdelaziz, S. Abdou, et H. Al-Barhamtoshy, « A large vocabulary system for Arabic online handwriting recognition », Pattern Anal. Appl., vol. 19, no 4, p. 1129–1141, 2016.
http://dx.doi.org/10.1007/s10044-015-0526-7

H. Choudhury, S. Mandal, et S. M. Prasanna, « Optimization of HMM parameters for online handwriting synthesis », in Region 10 Conference (TENCON), 2016 IEEE, 2016, p. 277–281.
http://dx.doi.org/10.1109/tencon.2016.7848006

Sarno, R., Sungkono, K., Hidden Markov Model for Process Mining of Parallel Business Processes, (2016) International Review on Computers and Software (IRECOS), 11 (4), pp. 290-300.
http://dx.doi.org/10.15866/irecos.v11i4.8700

I. Guyon, P. Albrecht, Y. Le Cun, J. Denker, et W. Hubbard, « Design of a neural network character recognizer for a touch terminal », Pattern Recognit., vol. 24, no 2, p. 105–119, 1991.
http://dx.doi.org/10.1016/0031-3203(91)90081-f

E. Poisson, C. Viard-Gaudin, et P. M. Lallican, « Réseaux de neurones à convolution: reconnaissance de l’écriture manuscrite non contrainte », Valgo 2001, no 01–02, 2001.
http://dx.doi.org/10.3845/ree.1997.080

Y. Le Cun et Y. Bengio, « Word-level training of a handwritten word recognizer based on convolutional neural networks », in Pattern Recognition, 1994. Vol. 2-Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on, 1994, vol. 2, p. 88–92.
http://dx.doi.org/10.1109/icpr.1994.576881

S. Marukatat, T. Artieres, R. Gallinari, et B. Dorizzi, « Sentence recognition through hybrid neuro-markovian modeling », in Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on, 2001, p. 731–735.
http://dx.doi.org/10.1109/icdar.2001.953886

K. Ni, P. Callier, et B. Hatch, « Writer Identification in Noisy Handwritten Documents », in Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on, 2017, p. 1177–1186.
http://dx.doi.org/10.1109/wacv.2017.136

Bahram, T., Benyettou, A., Ziadi, D., A Set of Features for Text-Independent Writer Identification, (2016) International Review on Computers and Software (IRECOS), 11 (10), pp. 898-906.
http://dx.doi.org/10.15866/irecos.v11i10.10347

W. Akram et M. A. Shah, « Online Signature Verification: A Survey on Authentication in Smartphones », in Advances in Ubiquitous Networking 2, Springer, 2017, p. 471–480.
http://dx.doi.org/10.1007/978-981-10-1627-1_37

A. Priya, S. Mishra, S. Raj, S. Mandal, et S. Datta, « Online and offline character recognition: A survey », in Communication and Signal Processing (ICCSP), 2016 International Conference on, 2016, p. 0967–0970.
http://dx.doi.org/10.1109/iccsp.2016.7754291

Y. Hamdi, A. Chaabouni, H. Boubaker, et A. M. Alimi, « Off-Lexicon Online Arabic Handwriting Recognition Using Neural Network », in Proc. of SPIE Vol, 2017, vol. 10341, p. 103410G–1.
http://dx.doi.org/10.1117/12.2268650

T. Saba, A. S. Almazyad, et A. Rehman, « Online versus offline Arabic script classification », Neural Comput. Appl., vol. 27, no 7, p. 1797–1804, 2016.
http://dx.doi.org/10.1007/s00521-015-2001-1

K. Jayech, M. A. Mahjoub, et N. E. B. Amara, « Synchronous Multi-Stream Hidden Markov Model for offline Arabic handwriting recognition without explicit segmentation », Neurocomputing, vol. 214, p. 958–971, 2016.
http://dx.doi.org/10.1016/j.neucom.2016.07.020

H. El Abed, V. Märgner, M. Kherallah, et A. M. Alimi, « Icdar 2009 online arabic handwriting recognition competition », in Document Analysis and Recognition, 2009. ICDAR’09. 10th International Conference on, 2009, p. 1388–1392.
http://dx.doi.org/10.1109/icdar.2009.284

R. Tlemsani et A. Benyettou, « Improved Dynamic Bayesian Networks Applied to Arabic on Line Characters Recognition », World Acad. Sci. Eng. Technol. Int. J. Comput. Electr. Autom. Control Inf. Eng., vol. 8, no 4, p. 600–605, 2014.
http://dx.doi.org/10.1109/icmcs.2012.6320148

A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, et K. J. Lang, « Phoneme recognition using time-delay neural networks », IEEE Trans. Acoust. Speech Signal Process., vol. 37, no 3, p. 328–339, 1989.
http://dx.doi.org/10.1109/29.21701

R. Zouari, H. Boubaker, et M. Kherallah, « Hybrid TDNN-SVM Algorithm for Online Arabic Handwriting Recognition », in International Conference on Hybrid Intelligent Systems, 2016, p. 113–123.
http://dx.doi.org/10.1007/978-3-319-52941-7_12

P. Singh et N. Tyagi, « Radial basis function for handwritten devanagari numeral recognition », Int. J. Adv. Comput. Sci. Appl., vol. 2, no 5, 2011.
http://dx.doi.org/10.14569/ijacsa.2011.020521

C. M. Bishop, Neural networks for pattern recognition. Oxford university press, 1995.
http://dx.doi.org/10.1201/9781420050646.ptb6

S. K. Prabhakar et H. Rajaguru, « Performance Analysis of ApEn as a Feature Extraction Technique and Time Delay Neural Networks, Multi Layer Perceptron as Post Classifiers for the Classification of Epilepsy Risk Levels from EEG Signals », in Computational Intelligence, Cyber Security and Computational Models, Springer, 2016, p. 89–97.
http://dx.doi.org/10.1007/978-981-10-0251-9_10

R. Tyasnurita, E. Özcan, et R. John, « Learning heuristic selection using a time delay neural network for open vehicle routing », 2017.
http://dx.doi.org/10.1109/cec.2017.7969477

J. B. Cornwell, B. Billingsley, Y. Zhan, et R. Lo, Display screen with animated graphical user interface. Google Patents, 2016.
http://dx.doi.org/10.2172/6888908

Y. Hamdi, A. Chaabouni, H. Boubaker, et A. M. Alimi, « Hybrid Neural Network and Genetic Algorithm for off-Lexicon Online Arabic Handwriting Recognition », in International Conference on Hybrid Intelligent Systems, 2016, p. 431–441.
http://dx.doi.org/10.1007/978-3-319-52941-7_43


Refbacks

  • There are currently no refbacks.



Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2024 Praise Worthy Prize