A Holistic Approach to Urdu Language Word Recognition using Deep Neural Networks
Published online first on May 6, 2021.
Urdu is one of the most popular languages in the world. It is a Persianized standard register of the Hindi language with considerable and valuable literature. While digital libraries are constantly replacing conventional libraries, a vast amount of Urdu literature is still handwritten. Digitizing this handwritten literature is essential to preserve it and make it more accessible. Nevertheless, the scarcity of Urdu Optical Character Recognition (OCR) research limits a digital library's scope to a manual document search. The limited research work in this area is mainly due to the complexity of Urdu Script. Unlike the English language, the Urdu writing style is cursive, bidirectional, and character shapes and sizes highly vary depending on their position. Holistic word recognition is found to be a better solution among many other text segmentation techniques as it takes the complete word into account instead of segmenting it explicitly or implicitly. For this project, the data of five different Urdu words were collected for training and testing a convolutional neural network and 96% recognition accuracy was achieved.
Keywords:word recognition, Urdu, deep learning, cursive writting
M. W. Sagheer, C. L. He, N. Nobile, and C. Y. Suen, "Holistic Urdu Handwritten Word Recognition Using Support Vector Machine," in 2010 20th International Conference on Pattern Recognition, Aug. 2010, pp. 1900–1903. DOI: https://doi.org/10.1109/ICPR.2010.468
A. Abidi, A. Jamil, I. Siddiqi, and K. Khurshid, "Word Spotting Based Retrieval of Urdu Handwritten Documents," in 2012 International Conference on Frontiers in Handwriting Recognition, Bari, Italy, Sep. 2012, pp. 331–336. DOI: https://doi.org/10.1109/ICFHR.2012.289
H. Bunke and P. S. P. Wang, Handbook of Character Recognition and Document Image Analysis. World Scientific, 1997. Chaudhuri, K. Mandaviya, P. Badelia, and S. K. Ghosh, Optical Character Recognition Systems for Different Languages with Soft Computing. Springer International Publishing, 2017.
N. H. Khan and A. Adnan, "Urdu Optical Character Recognition Systems: Present Contributions and Future Directions," IEEE Access, vol. 6, pp. 46019–46046, 2018. DOI: https://doi.org/10.1109/ACCESS.2018.2865532
U. Pal and A. Sarkar, "Recognition of Printed Urdu Script," in Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2, USA, Aug. 2003, pp. 1183-1187.
Q. U. A. Akram and S. Hussain, "Improving Urdu Recognition Using Character-Based Artistic Features of Nastalique Calligraphy," IEEE Access, vol. 7, pp. 8495–8507, 2019. DOI: https://doi.org/10.1109/ACCESS.2018.2887103
Z. Ahmad, J. K. Orakzai, and I. Shamsher, "Urdu compound Character Recognition using feed forward neural networks," in 2009 2nd IEEE International Conference on Computer Science and Information Technology, Beijing, China, Aug. 2009, pp. 457–462. DOI: https://doi.org/10.1109/ICCSIT.2009.5234683
V. Lavrenko, T. M. Rath, and R. Manmatha, "Holistic word recognition for handwritten historical documents," in First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings., Palo Alto, CA, USA, Jan. 2004, pp. 278–287.
N. P. T. Kishna and S. Francis, "Intelligent tool for Malayalam cursive handwritten character recognition using artificial neural network and Hidden Markov Model," in 2017 International Conference on Inventive Computing and Informatics (ICICI), Coimbatore, India, Nov. 2017, pp. 595–598. DOI: https://doi.org/10.1109/ICICI.2017.8365201
M. Jaderberg, K. Simonyan, A. Vedaldi, and A. Zisserman, "Reading Text in the Wild with Convolutional Neural Networks," International Journal of Computer Vision, vol. 116, no. 1, pp. 1–20, Jan. 2016. DOI: https://doi.org/10.1007/s11263-015-0823-z
X. Chen and A. L. Yuille, "Detecting and reading text in natural scenes," in Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., Washington, DC, USA, Jun. 2004, vol. 2.
P. R. Cavalin, A. de Souza Britto, F. Bortolozzi, R. Sabourin, and L. E. S. Oliveira, "An implicit segmentation-based method for recognition of handwritten strings of characters," in Proceedings of the 2006 ACM symposium on Applied computing, New York, NY, USA, Apr. 2006, pp. 836–840. DOI: https://doi.org/10.1145/1141277.1141468
M. Ghosh, R. Ghosh, and B. Verma, "A fully automated offline handwriting recognition system incorporating rule based neural network validated segmentation and hybrid neural network classifier," International Journal of Pattern Recognition and Artificial Intelligence, vol. 18, no. 7, pp. 1267–1283, Nov. 2004. DOI: https://doi.org/10.1142/S0218001404003654
N. Sivashanmugam, "A Study of Various Segmentation Techniques for Cursive Handwritten Words Recognition," International Journal of Modern Trends in Engineering and Research, 2015.
O. Alsharif and J. Pineau, "End-to-End Text Recognition with Hybrid HMM Maxout Models," arXiv:1310.1811 [cs], Oct. 2013, Accessed: Apr. 23, 2021. [Online]. Available: http://arxiv.org/abs/1310.1811.
M. Jaderberg, A. Vedaldi, and A. Zisserman, "Speeding up Convolutional Neural Networks with Low Rank Expansions," arXiv:1405.3866 [cs], May 2014, Accessed: Apr. 23, 2021. [Online]. Available: http://arxiv.org/abs/1405.3866. DOI: https://doi.org/10.5244/C.28.88
S. Hijazi, R. Kumar, and C. Rowen, "Using Convolutional Neural Networks for Image Recognition." Cadence Design Systems Inc, 2015.
S. Sahel, M. Alsahafi, M. Alghamdi, and T. Alsubait, "Logo Detection Using Deep Learning with Pretrained CNN Models," Engineering, Technology & Applied Science Research, vol. 11, no. 1, pp. 6724–6729, Feb. 2021. DOI: https://doi.org/10.48084/etasr.3919
U. Khan, K. Khan, F. Hassan, A. Siddiqui, and M. Afaq, "Towards Achieving Machine Comprehension Using Deep Learning on Non-GPU Machines," Engineering, Technology & Applied Science Research, vol. 9, no. 4, pp. 4423–4427, Aug. 2019. DOI: https://doi.org/10.48084/etasr.2734
How to Cite
MetricsAbstract Views: 361
PDF Downloads: 250
Copyright (c) 2021 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.