Multi-digit Handwritten Sindhi Numerals Recognition using SOM Neural Network.

Asghar Ali Chandio; Akhtar Hussain Jalbani; MEHWISH LEGHARI; Shafique Ahmed Awan

Author(s)

Asghar Ali Chandio Department of Information Technology, Quaid-e-Awam University of Engineering, Science & Technology, Nawabshah, Pakistan

Akhtar Hussain Jalbani Department of Information Technology, Quaid-e-Awam University of Engineering, Science & Technology, Nawabshah, Pakistan

MEHWISH LEGHARI Department of Information Technology, Quaid-e-Awam University of Engineering, Science & Technology, Nawabshah, Pakistan

Shafique Ahmed Awan Department of Computer Science & Information Technology, Benazir Bhutto Shaheed University, Layari Karachi, Pakistan

Abstract

In this research paper a multi-digit Sindhi handwritten numerals recognition system using SOM Neural Network is presented. Handwritten digits recognition is one of the challenging tasks and a lot of research is being carried out since many years. A remarkable work has been done for recognition of isolated handwritten characters as well as digits in many languages like English, Arabic, Devanagari, Chinese, Urdu and Pashto. However, the literature reviewed does not show any remarkable work done for Sindhi numerals recognition. The recognition of Sindhi digits is a difficult task due to the various writing styles and different font sizes. Therefore, SOM (Self-Organizing Map), a NN (Neural Network) method is used which can recognize digits with various writing styles and different font sizes. Only one sample is required to train the network for each pair of multi-digit numerals. A database consisting of 4000 samples of multi-digits consisting only two digits from 10-50 and other matching numerals have been collected by 50 users and the experimental results of proposed method show that an accuracy of 86.89% is achieved.

Publication Details

Page(s) 901-908

DOI DOI not available

Published Journal: Mehran University Research Journal of Engineering and Technology, Volume: 36, Issue: 4, Year: 2017

Request the full text from PASTIC

Keywords

Self-Organizing Ma, Multi-Digits Recognition, Multi-Font DigitsRecognition, Sindhi Handwritten Numerals Recognition

References

Charles, P.K., Harish, V., Swathi, M., and Deepthi, C.H.. “A Review on the Various Techniques Used for Optical Character Recognition”, International Journal of Engineering Research and Applications, Volume 2, No. 1, pp. 659-662, 2012.

Kapoor, V., and Gupta, P., “Digit Recognition System by using Back Propagation Algorithm”, International Journal of Computer Applications, Volume 83, No. 8, pp. 33-36, 2013.

Singh, P., Verma, A., and Chaudhari, N.S., “Handwritten Devnagari Digit Recognition using Fusion of Global and Local Features”, International Journal of Computer Applications, Volume 89, No. 1, pp. 6-12, 2014.

Sindhi Language, “In Sindhi Language Authority”, Retrieved May 12, 2015, from http://sl.sindhila.org/en/ about-sindhi-language

Leghari, M., and Rahman, M.U., “Towards Transliteration between Sindhi Scripts by using Roman Script”, Conference on Language and Technology, National Language Authority, Pakistan, 2010.

Dhandra, B.V., Malemath, V.S., Mallikarjun, H., and Hegadi, R., “Multi-Font Numeral Recognition without Thinning Based on Directional Density of Pixels”, IEEE 1st International Conference on Digital Information Management, pp. 157-160, 2006.

Hassanpour, H., and Samadiani, N., “Recognition of Multi-Font English Numerals using SOM Neural Network”, International Journal of Computer Applications, Volume 98, No. 4, pp. 37-41, 2014.

Montazer, G.A., Saremi, H.Q., and Khatibi, V., “A Neuro-Fuzzy Inference Engine for Farsi Numeral Characters Recognition”, Expert Systems with Applications, Volume 37, No. 9, pp. 6327-6337, 2010.

Santosh, A.N., Navaneetha, G., Preethi, G.V., and Babu, T.K., “An Approach to Multi-Font Numeral Recognition” IEEE Conference on TENCON Region, pp. 1-4, 2007.

Goyal, H.R., and Koolagudi, S., “Hindi Number Recognition using GMM”, International Journal of Computer Applications, Volume 63, No. 21, 2013.

Kapoor, V., and Gupta, P., “Digit Recognition System by using Back Propagation Algorithm”, International Journal of Computer Applications, Volume 83, No. 8, pp. 33-36, 2013

Bazrafkan, M., and Broumandnia, A., “A New String Matching Algorithm and its Application in Hand-Written Digits Recognition”, International Journal of Computer Applications, Volume 70, No. 17, pp. 13-16, 2013.

Rani, G.S.R., and Dhir, R., “Handwritten Gurmukhi Numeral Recognition using Zone-Based Hybrid Feature Extraction Techniques”, International Journal of Computer Applications, Volume 47, No. 21, pp. 24-29, 2012.

Zaghloul, R.I., Enas, D.M.B., and AlRawashdeh, F., “Recognition of Hindi (Arabic) Handwritten Numerals”, American Journal of Engineering and Applied Sciences, Volume 5, No. 2, pp. 132, 2012.

Charfi, M., “A New Approach for Arabic Handwritten Postal Addresses Recognition”, arXiv Preprint arXiv, Volume 1204, No. 1678, 2012.

Salimi, H., and Giveki, D., “Farsi/Arabic Handwritten Digit Recognition Based on Ensemble of SVD Classifiers and Reliable Multi-Phase PSO Combination Rule”, International Journal on Document Analysis and Recognition, Volume 16, No. 4, pp. 371-386, 2013.

Diem, M., Fiel, S., Garz, A., Keglevic, M., Kleber, F., and Sablatnig, R., “Competition on Handwritten Digit Recognition”, IEEE 12th International Conference on Document Analysis and Recognition pp. 1422-1427, 2013.

Azad, R., Davami, F., and Shayegh, H.R., “Recognition of Handwritten Persian/Arabic Numerals Based on Robust Feature Set and K-NN Classifier”, arXiv Preprint arXiv, Volume 1407, No. 6492, 2014

Javidi, M.M., and Sharifizadeh, F., “A Modified Decision Templates Method for Persian Handwritten Digit Recognition”, Journal of American Science, Volume 8, No. 1, 2012.

Sagheer, M.W., He, C.L., Nobile, N., and Suen, C.Y., “A New Large Urdu Database for Off-Line Handwriting Recognition”, Image Analysis and Processing – ICIAP, pp. 538-546, Springer Berlin/ Heidelberg, 20

Javed, L., Shafi, M., Khattak, M., and Ullah, N., “Hand- Written Urdu Numerals Recognition using Kohonen Self Organizing Maps”, Sindh University Research Journal (Science Series), Volume 47, No. 3, Jamshoro, Pakistan, 2015.