Effective Tamil Character Recognition Using Supervised Machine Learning Algorithms

Authors

  • Dr. S. Suriya Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
  • S. Nivetha Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
  • P. Pavithran Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
  • Ajay Venkat S. Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
  • Sashwath K. G. Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
  • Elakkiya G. Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India

DOI:

https://doi.org/10.4108/eetel.v8i2.3025

Keywords:

Computational Linguistics, Character recognition, distortions, Convolutional Neural Networks, Multi-layer neural networks, back-propagation algorithm, pixel images, preprocessing, trained network

Abstract

Computational linguistics is the branch of linguistics in which the techniques of computer science are applied to the analysis and synthesis of language and speech. The main goals of computational linguistics include: Text-to- speech conversion, Speech-to-text conversion and Translating from one language to another. A part of Computational Linguistics is the Character recognition. Character recognition has been one of the active and challenging research areas in the field of image processing and pattern recognition. Character recognition methodology mainly focuses on recognizing the characters irrespective of the difficulties that arises due to the variations in writing style. The aim of this project is to perform character recognition for of one of the complex structures of south Indian language ‘Tamil’ using a supervised algorithm that increases the accuracy of recognition. The novelty of this system is that it recognizes the characters of the Predominant Tamil Language. The proposed approach is capable of recognizing text where the traditional character recognition systems fails, notably in the presence of blur, low contrast, low resolution, high image noise, and other distortions. This system uses Convolutional Neural Network Algorithm that are able to exact the local features more accurately as they restrict the receptive fields of the hidden layers to be local. Convolutional Neural Networks are a great kind of multi-layer neural networks that uses back-propagation algorithm. Convolutional Neural Networks are used to recognize visual patterns directly from pixel images with minimal preprocessing. This trained network is used for recognition and classification. The results show that the proposed system yields good recognition rates.

References

Vani, V. and Ananthalakshmi, S.R., Soft computing approaches for character credential and word prophecy analysis with stone encryptions. Soft Computing, pp.1-14

Ramya, J., Kumar, G.K.R. and Peniel, C.J., 2019, March. ‘Agaram’–Web Application of Tamil Characters Using Convolutional Neural Networks and Machine Learning. In International Conference on Emerging Current Trends in Computing and Expert Technology (pp. 670-680). Springer, Cham

Kowsalya, S. and Periasamy, P.S., 2019. Recognition of Tamil handwritten character using modified neural network with aid of elephant herding optimization. Multimedia Tools and Applications, 78(17), pp.25043-25061.

Kavitha, B.R. and Srimathi, C., 2019. Benchmarking on offline Handwritten Tamil Character Recognition using convolutional neural networks. Journal of King Saud University-Computer and Information Sciences.

Raj, M.A.R. and Abirami, S., 2019. Structural representation-based off-line Tamil handwritten character recognition. Soft Computing, pp.1-26.

Subashini, A. and Kodikara, N.D., 2011, August. A novel SIFT-based codebook generation for handwritten Tamil character recognition. In 2011 6th International Conference on Industrial and Information Systems (pp. 261- 264). IEEE.

Bhattacharya, U., Ghosh, S.K. and Parui, S., 2007, September. A two-stage recognition scheme for handwritten Tamil characters. In Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) (Vol. 1, pp. 511-515). IEEE.

Elakkiya, V., Muthumani, I. and Jegajothi, M., 2017. Tamil text recognition using KNN classifier. Advances in Natural and Applied Sciences, 11(7), pp.41-46

Liyanage, C., Nadungodage, T. and Weerasinghe, R., 2015, August. Developing a commercial grade Tamil OCR for recognizing font and size independent text. In 2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer) (pp. 130-134). IEEE

Manisha, S. and Sharmila, T.S., 2017. Effective Printed Tamil Text Segmentation and Recognition Using Bayesian Classifier. In Computational Intelligence in Data Mining (pp. 729-738). Springer, Singapore.

Ramanan, M., Ramanan, A. and Charles, E.Y.A., 2015, August. A hybrid decision tree for printed Tamil character recognition using SVMs. In 2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer) (pp. 176-181). IEEE.

Shivsubramani, K., Loganathan, R., Srinivasan, C.J., Ajay, V. and Soman, K.P., 2007. Multiclass hierarchical SVM for recognition of printed Tamil characters. TC, 2, p.2.

Stephen, P. and Jaganathan, S., 2014, March. Linear regression for pattern recognition. In 2014 International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE) (pp. 1-6). IEEE.

Suresh, R.M., Arumugam, S. and Ganesan, L., 1999, September. Fuzzy approach to recognize handwritten Tamil characters. In Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No. PR00300) (pp. 459-463). IEEE.

Suresh, R.M. and Arumugam, S., 2007. Fuzzy technique based recognition of handwritten characters. Image and Vision Computing, 25(2), pp.230-239.

Kunwar, R., Pal, U. and Blumenstein, M., 2013, November. Semi-supervised online learning of handwritten characters using a bayesian classifier. In 2013 2nd IAPR Asian Conference on Pattern Recognition (pp. 717-721). IEEE.

Gandhi, R.I. and Iyakutti, K., 2009. An attempt to recognize handwritten Tamil character using Kohonen SOM. International Journal of Advanced Networking and Applications, 1(3), pp.188-192.

Banumathi, P. and Nasira, G.M., 2011, July. Handwritten Tamil character recognition using artificial neural networks. In 2011 International Conference on Process Automation, Control and Computing (pp. 1-5). IEEE.

Venkatesh, J. and Sureshkumar, C., 2009. Tamil handwritten character recognition using kohonon's self organizing map. International Journal of Computer Science and Network Security, 9(12), pp.156-161.

Web References

https://link.springer.com/article/10.1007/s00500-019-03978-5

https://searchenterpriseai.techtarget.com/definition/computational-linguistics

https://developers.google.com/machine-learning/clustering/algorithm/advantages-disadvantages

https://www.researchgate.net/post/What_is_the_pros_and_cons_of_Convolutional_neural_networks

https://link.springer.com/article/10.1007/s00500-019-03978-5

https://en.wikipedia.org/wiki/Convolutional_neural_network

https://plato.stanford.edu/entries/computational-linguistics/

http://ijarcet.org/wp-content/uploads/IJARCET-VOL-1-ISSUE-4-131-133.pdf

https://www.google.com/search?q=block+diagram+for+the+character+recognition

https://www.slideshare.net/nikbharat/project-report-of-ocr-recognition

https://www.analyticsvidhya.com/blog/2017/09/naive-bayes-explained/

https://www.researchgate.net/profile/Elviz_Ismayilov/publication/338420222_Parallel_Solution_Of_Features

_Subset_Selection_Process_For_Hand-Printed_Character_Recognition/

https://www.geeksforgeeks.org/project-idea-character-recognition-from-image/

https://towardsdatascience.com/support-vector-machines-svm-c9ef22815589

https://www.researchgate.net/post/What_are_pros_and_cons_of_decision_tree_versus_other_classifier_as

_KNN_SVM_NN

https://www.coursehero.com/file/ps5vu3/What-are-the-Pros-and-Cons-of-Naive-Bayes-Pros- httpswwwanalyticsvidhyacomwp/

https://www.researchgate.net/publication/323547763_Handwritten_Character_Recognition_HCR_USING_ NEURAL_NETWORK

https://arxiv.org/pdf/1804.02864.pdf

https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm

https://www.slideshare.net/chiranjeeviadi/hand-written-character-recognition-using-neural-networks

https://www.slideshare.net/chiranjeeviadi/hand-written-character-recognition-using-neural-networks

https://www.academia.edu/258529/Requirements_for_the_Design_of_a_Handwriting_Recognition_Based_ Writing_Interface_for_Children

https://senior.ceng.metu.edu.tr/2016/teamtrio/docs/srs.pdf

https://www.researchgate.net/figure/Advantages-and-disadvantages-of-fuzzy-logic-control- techniques_tbl7_323441631

https://electricalvoice.com/kohonen-self-organizing-maps-algorithm-advanatges/

https://plato.stanford.edu/entries/computational-linguistics/

https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=+literature+survey+on+Tamil+character+reco gnition&btnG=

https://www.guru99.com/what-is-fuzzy-logic.html

https://monkeylearn.com/blog/introduction-to-support-vector-machines-svm/

http://www.academia.edu/Documents/in/Literature_Review

Downloads

Published

08-02-2023

How to Cite

[1]
D. S. Suriya, S. Nivetha, P. Pavithran, A. Venkat S., S. K. G., and E. G., “Effective Tamil Character Recognition Using Supervised Machine Learning Algorithms”, EAI Endorsed Trans e-Learn, vol. 8, no. 2, p. e1, Feb. 2023.