Current Science

Open Access Open Access  Restricted Access Subscription Access

Repossession and Recognition System: Transliteration of Antique Tamil Brahmi Typescript


Affiliations
1 Department of Computer Science and Engineering, Easwari Engineering College, Chennai 600 089, India
 

Tamil is among the ancient languages in the world with a rich literature. Recognition of antique Tamil scripts is difficult and different from the present form of the language. The character recognition of Brahmi script poses a big challenge even today. In this paper, a new technique for extracting the features is proposed, and converting the ancient Tamil script into the present form. Initially, the system is implemented by performing the pre-processing steps. Then the characters are individually separated using the segmentation process. The processed image undergoes a new feature extraction technique, where the system applies a chi-square test to check whether all the zoning feature values of the image are independent or dependent. The characters are recognized from the extracted features using neural networks. NNTool is employed to train the featured image and the data are compared with the database to recognize the Brahmi characters. The feature extraction technique along with the neural network achieved recognition rate accuracy of 91.3% and error rate of 8.7% using the confusion matrix. Our experiment has been simulated using MATLAB.

Keywords

Ancient Script, Chi-square Test, Confusion Matrix, Feature Extraction Technique, Neural Networks.
User
Notifications
Font Size

  • Selvakumar, P. and Ganesh, S. H., Tamil character recognition using canny edge detection algorithm. In Computing and Communication Technologies, 2017, pp. 250–254.

  • Mahalakshmi, M. and Sharavanan Malathi, Ancient Tamil script and recognition and translation using LabVIEW. In International Conference on Communication and Signal Processing, 2013, pp. 1021–1026.

  • Rajakumar, S. and Subbiah Bharathi, V., Century identification and recognition of ancient Tamil character recognition. Int. J. Comput. Appl., 2011, 26(4), 32–35.

  • Vellingiriraj, E. K. and Balasubramanie, P., Recognition of Ancient Tamil handwritten characters in palm manuscripts using genetic algorithm. Int. J. Sci. Eng. Technol., 2016, 2(5), 342–346.

  • Janani, G., Vishalini, V. and Mohan Kumar, P., Recognition and analysis of Tamil inscriptions and mapping using image processing techniques. IEEE Trans. Sci, Technol. Eng. Manage., 2016.

  • Subramani Kavitha and Murugavalli, S., A novel binarization method for degraded Tamil palm leaf images. In IEEE Eighth International Conference on Advanced Computing, 2016.

  • Banumathi, P. and Nasira, G. M., Handwritten Tamil character recognition using artificial neural networks. IEEE Trans., 2011.

  • Jagadeesh Kannan, R., Prabhakar, R. and Suresh, R. M., Off-line cursive handwritten Tamil character recognition. IEEE Trans. Int. Conf. Security Technol., 2008.

  • Kavitha, A. S., Shivakumara, P. and Hemantha Kumar, G., Skewness and nearest neighbour based approach for historical document classification. IEEE Trans. Commun. Syst. Network Technol., 2013.

  • Subashini and Kodikara, N. D., A novel SIFT-based codebook generation for handwritten Tamil character recognition. IEEE Trans. Ind. Inf. Syst., 2011.

  • Pirlo, G. and Impedovo, D., Adaptive membership functions for handwritten character recognition by Voronoi-based image zoning. IEEE Trans. Image Process., 2012, 21(9).

  • Boufenar, C., Batouche, M. and Schoenauer, M., An artificial immune system for offline isolated handwritten Arabic character recognition. Springer Trans. Evol. Syst., 2016.

  • Rajakumar, S. and Subbiah Bharathi, V., Ancient Tamil script recognition from stone inscriptions using slant removal method. IEEE Trans. Elect., Electron. Biomed. Eng., 2012.

  • Bhuvaneswari, G. and Subbiah Bharathi, V., An efficient method for digital imaging of ancient stone inscriptions. Curr. Sci., 2016, 245–250.

  • Medhi, Kalyanbrat and Sanjib Kr Kalita, Assamese character recognition using zoning feature. In Advances in Electronics, Communication and Computing, Springer, Singapore, 2018, pp. 371– 380.

  • Vellingiriraj, E. K., Balamurugan, M. and Balasubramanie, P., Information extraction and text mining of ancient vattezhuthu characters in historical documents using image zoning. IEEE Trans. Int. Conf. Asian Language Process., 2016.

  • Kale, K. V., Deshmukh, P. D., Chavan, S. V., Kazi, M. M. and Rode, Y. S., Zernike moment feature extraction for handwritten Devanagari compound character recognition. In IEEE Science and Information Conference, 2013, pp. 459–466.

  • Abandah, G. A., Jamour, F. T. and Qaralleh, E. A., Recognizing handwritten Arabic words using grapheme segmentation and recurrent neural networks. Int. J. Doc. Anal. Recogn., 2014, 17(3), 275–291.

  • Plamondon, R. and Srihari, S. N., Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell., 2006, 22(1), 63–84.

  • Sumathi, C. P. and Karpagavalli, S., Techniques and methodologies for recognition of Tamil typewritten and handwritten characters: a survey. Int. J. Comput. Sci. Eng. Surv., 2012, 3(6), 23–35.

  • Indra Gandhi, R. and Iyakutti, K., An attempt to recognize handwritten Tamil character using Kohonen SOM. Int. J. Adv. Net. Appl., 2009, 1(3), 188–192.

  • http://en.wikipedia.org/wiki/brami_script

  • Suganya, T. S. and Murugavalli, S., A survey on character recognitions in Tamil scripts using OCR, 2012.

  • JeyaGreeba, M. V. and Bhuvaneswari, G., Recognition of ancient Tamil characters in stone inscription using improved feature extraction. Int. J. Recent Develop. Eng. Technol., 2014, 2(3), 38–41.

  • Zernike, F., Physica, 1934, 1, 689.

  • Wang, Qiu-Feng Yin, Fei and Liu, Cheng-Lin, Handwritten Chinese text recognition by integrating multiple contexts. IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34(8), 1469–1481.

  • Pornpanomchai, C., Wongsawangtham, V., Jeungudomporn, S. and Chatsumpun, N., Thai handwritten character recognition by genetic algorithm (THCRGA). IACSIT J. Eng. Technol., 2011, 3(2), 148–153.

  • Jose, T. M. and Wahi, A., Recognition of Tamil handwritten characters using Daubechies wavelet transforms and feed-forward backpropagation network. Int. J. Comput. Appl., 2013, 64(8), 0975–8887.

  • Tharwat, A., Classification assessment methods. Applied Computing and Informatics, 2018.


Abstract Views: 402

PDF Views: 131




  • Repossession and Recognition System: Transliteration of Antique Tamil Brahmi Typescript

Abstract Views: 402  |  PDF Views: 131

Authors

S. Brindha
Department of Computer Science and Engineering, Easwari Engineering College, Chennai 600 089, India
S. Bhuvaneswari
Department of Computer Science and Engineering, Easwari Engineering College, Chennai 600 089, India

Abstract


Tamil is among the ancient languages in the world with a rich literature. Recognition of antique Tamil scripts is difficult and different from the present form of the language. The character recognition of Brahmi script poses a big challenge even today. In this paper, a new technique for extracting the features is proposed, and converting the ancient Tamil script into the present form. Initially, the system is implemented by performing the pre-processing steps. Then the characters are individually separated using the segmentation process. The processed image undergoes a new feature extraction technique, where the system applies a chi-square test to check whether all the zoning feature values of the image are independent or dependent. The characters are recognized from the extracted features using neural networks. NNTool is employed to train the featured image and the data are compared with the database to recognize the Brahmi characters. The feature extraction technique along with the neural network achieved recognition rate accuracy of 91.3% and error rate of 8.7% using the confusion matrix. Our experiment has been simulated using MATLAB.

Keywords


Ancient Script, Chi-square Test, Confusion Matrix, Feature Extraction Technique, Neural Networks.

References





DOI: https://doi.org/10.18520/cs%2Fv120%2Fi4%2F654-665