Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks

  • Mahsa Aliakbarzadeh Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
  • Farbod Razzazi Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran. http://orcid.org/0000-0003-4970-8117
Keywords: Handcrafted Features, End-to-End Identification, GRU, Online Writer Identification

Abstract

Conventional methods in writer identification mostly rely on hand-crafted features to represent the characteristics of different handwritten scripts. In this paper, we propose an end-to-end model for online text-independent writer identification on Persian/Arabic online handwritten scripts by using Gated Recurrent Unit (GRU) neural networks. The method does not require any specific knowledge for handwriting data analysis. Because of the exclusive ability of deep neural networks, we just represented our data by Random Strokes (RS) representations, which are differential horizontal and vertical coordinates extracted from different handwritings with a predefined length. This representation is a context independent representation. Therefore, this writer identification at RS level is more general than character level or word level in identification systems, which require character or word segmentation. The RS representation is then fed to a GRU neural network to represent the sequence for final classification. All RS features of a writer are then classified independently, and in the final stage, the posterior probabilities are averaged to make the final decision. Experiments on KHATT database, which consists of online handwritings of Arabic writers, gave us 100% accuracy on 10 writers and 76% accuracy on 50 writers, which is much better than previous works on online Persian/Arabic writer identification.  

Author Biography

Farbod Razzazi, Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
Dr. Razzazi is an associate professor in department of Electrical and computer Engineering of IAU- Science and Research Branch. His specialty is on image and speech processing and machine learning aspects of speech and image signals. Education: BSc: Sharif University of Technology MSc: Sharif University of Technology PhD: Amirkabir University of Technology

References

[1] Emadi, M., & Jafar Pour, M. , " Improving Human's Finger Knuckle Identification using High Order Zernike Moments”, Majlesi Journal of Electrical Engineering, Vol. 14(1), pp. 119-125, 2020.
[2] V.Moradi, F.Razzazi, A.Behrad ” Recognition of Handwritten Persian Two-digit Numerals Using a Novel Hybrid SVM/HMM algorithm”, Majlesi Journal of Electrical Engineering, Vol. 10(3), 2016.
[3] R. Hanusiak, L.S. Oliveira, E. Justino, R. Sabourin, “Writer verification using texture-based features, International Journal on Document Analysis and Recog- nition “, pp. 213–226.580, 2012.
[4] Li. Bangy, Zhenan Sun, Tieniu Tan, “Hierarchical shape primitive features for online text-independent writer identification”, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 986-990,2009.
[5] M. Bulacu, L. Schomaker, A. Brink, “Text-independent writer identification and verification on offline Arabic handwriting”, in: International Conference on Document Analysis and Recognition, pp. 769–773, 2007.
[6] Li, Bangy, Zhenan Sun, Tieniu Tan, “Hierarchical shape primitive features for online text-independent writer identification”, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 986-990,2009.
[7] X. Wu, Y. Tang, W. Bu,” Offline text-independent writer identification based on scale invariant feature transform”, IEEE Transactions on Information Forensics and Security, Vol. 9 (3), pp. 526–53, 2014.
[8] Guoxian TAN, “Writing style modelling based on grapheme distributions: application to on-line writer identification”, Thesis in Nanyang Technological university, 2013.
[9] D. Bertolini, LS Oliveira, E Justino, R Sabourin, “Texture based descriptor for writer identification and verification ”, in Elsevier, 2013
[10] Li. Bangy, Zhenan Sun, Tieniu Tan, "Online Text-Independent Writer Identification Based on Stroke's Probability Distribution Function", International Conference on Biometrics Springer, Vol. 4642, pp. 201-210,2007.
[11] Weixin Yang, Lianwen Jin, Manfei Liu, “Deep Writer ID: An End- to-End Online Text- Independent Writer Identification System”, In IEEE Intelligent Systems, 2016.
[12] Hung Tuan Nguyen, Cuong Tuan Nguyen, "Text-independent writer identification using convolutional neural network”, Pattern Recognition Elsevier, 2019.
[13] Xu-Yao Zhang, Guo-Sen Xie,”End-to-End Online Writer Identification With Recurrent Neural Network”, IEEE transactions on human-machine systems, Vol. 47, No. 2, 2017.
[14] Thameur Dhieb, Wael Ouarda,” Online Arabic Writer Identification based on BetaElliptic Mode”, 15th International Conference on Intelligent Systems Design and Applications, At Marrakesh, Morroco, 2016
[15] http://onlinekhatt.ideas2serve.net/
[16] Mariem GARGOURI, Slim KANOUN, “Text-independent Writer Identification on Online Arabic Handwriting”, 12th International Conference on Document Analysis and Recognition, 2013
Published
2020-09-01
How to Cite
Aliakbarzadeh, M., & Razzazi, F. (2020). Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks. Majlesi Journal of Electrical Engineering, 14(3), 73-79. https://doi.org/https://doi.org/10.29252/mjee.14.3.9
Section
Articles