An Online Numeral Recognition System Using Improved Structural Features – A Unified Method for Handwritten Arabic and Persian Numerals

Authors

  • Jaafar M. Alghazo College of Computer Engineering and Sciences, Prince Mohammad bin Fahd University, Khobar, Saudi Arabia.
  • Ghazanfar Latif College of Computer Engineering and Sciences, Prince Mohammad bin Fahd University, Khobar, Saudi Arabia.
  • Ammar Elhassan College of Computer Engineering and Sciences, Prince Mohammad bin Fahd University, Khobar, Saudi Arabia.
  • Loay Alzubaidi College of Computer Engineering and Sciences, Prince Mohammad bin Fahd University, Khobar, Saudi Arabia.
  • Ahmad Al-Hmouz Department of Electrical and Computer Engineering, King Saud University, Riyadh Saudi Arabia.
  • Rami Al-Hmouz Faculty Of Information Technology, Middle East University, Amman, Jordan.

Keywords:

Arabic Numerals, Persian Numerals, Structural Features, Random Forest, Numerals Recognition, Digit Recognition, Arabic Digits, Persian Digits,

Abstract

With the advances in machine learning techniques, handwritten recognition systems also gained importance. Though digit recognition techniques have been established for online handwritten numerals, an optimized technique that is writer independent is still an open area of research. In this paper, we propose an enhanced unified method for the recognition of handwritten Arabic and Persian numerals using improved structural features. A total of 37 structural based features are extracted and Random Forest classifier is used to classify the numerals based on the extracted features. The results of the proposed approach are compared with other classifiers including Support Vector Machine (SVM), Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN). Four different well-known Arabic and Persian databases are used to validate the proposed method. The obtained average 96.15% accuracy in recognition of handwritten digits shows that the proposed method is more efficient and produces better results as compared to other techniques.

References

Musleh, D., Halawani, K. and Mahmoud, S., 2015, Fuzzy Modeling for Handwritten Arabic Numeral Recognition, International Arab Journal of Information Technology (IAJIT), 14(4), pp. 1-10.

Azeem, S.A., El Meseery, M. and Ahmed, H., 2012, Online Arabic Handwritten Digits Recognition. In International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 135-140.

Abuzaraida, M. A., Zeki, A. M., & Zeki, A. M. (2015). Online Recognition System for Handwritten Arabic Digits. In Proceeding of the The 7th International Conference on Information Technology, Amman, Jordan,pp. 45-49.

Ramakrishnan, A.G. and Urala, K.B., 2013, August. Global and local features for recognition of online handwritten numerals and Tamil characters. In Proceedings of the 4th International Workshop on Multilingual OCR, pp. 16-21.

Azeem, S.A. and El Meseery, M., 2011, December. Arabic handwriting recognition using concavity features and classifier fusion. In 10th International Conference on Machine Learning and Applications and Workshops (ICMLA), 2011, pp. 200-203.

Keysers, D., Deselaers, T., Rowley, H.A., Wang, L.L. and Carbune, V., 2016. Multi-Language Online Handwriting Recognition. IEEE transactions on pattern analysis and machine intelligence, pp. 1-14.

Pal, A., Khonglah, B.K., Mandal, S., Choudhury, H., Prasanna, S.R.M., Rufiner, H.L. and Balasubramanian, V.N., 2016, March. Online Bengali handwritten numerals recognition using Deep Autoencoders. In Twenty Second National Conference on Communication (NCC), pp. 1-6.

Ghods, V. and Sohrabi, M.K., 2016. Online Farsi Handwritten Character Recognition Using Hidden Markov Model. JCP, 11(2), pp.169-175.

Jan, Z., Shabir, M., Khan, M.A., Ali, A. and Muzammal, M., 2016. Online Urdu Handwriting Recognition System Using Geometric Invariant Features. Nucleus, 53(2), pp.89-98.

Moradi, V., Razzazi, F. and Behrad, A., 2016. Recognition of Handwritten Persian Two-digit Numerals Using a Novel Hybrid SVM/HMM algorithm. Majlesi Journal of Electrical Engineering, 10(3), pp. 19-25.

Zarro, R.D. and Anwer, M.A., 2016. Recognition-based online Kurdish character recognition using hidden Markov model and harmony search. Engineering Science and Technology, an International Journal,pp. 1-12.

Malallah, F.L., Saeed, M.G., Aziz, M.M., Arigbabu, O.A. and Ahmad, S.M.S., 2016. Off-Line Arabic (Indian) Numbers Recognition Using Expert System. International Journal of Advanced Computer Science and Applications, 7(4), pp.397-406.

Salouan, R., Safi, S. and Bouikhalene, B., 2014. Printed eastern arabic noisy numerals recognition using hidden markov model and support vectors machine. International Journal of Innovation and Applied Studies, 9(3), pp.1032-1042.

El Kessab, B., Daoui, C., Boukhalene, B. and Salouan, R., 2014. A Comparative Study between the K-Nearest Neighbors and the MultiLayer Perceptron for Cursive Handwritten Arabic Numerals Recognition. International Journal of Computer Applications, 107(21), pp. 25-30.

Al_barraq, M.O. and Mehrotra, S.C., 2015. Recognition of Arabic Handwritten Amount in Cheque through Windowing Approach. International Journal of Computer Applications, 115(10), pp. 33-38.

Azad, R., Davami, F. and Boroujeni, H.S., 2013. Recognition of handwritten Persian/Arabic numerals based on robust feature set and K-NN classifier. International Journal of Computer and Information Technologies, 1(3), pp.220-230.

Cecotti, H., 2016. Active graph based semi-supervised learning using image matching: application to handwritten digit recognition. Pattern Recognition Letters, 73(1), pp.76-82.

Assayony, M.O. and Mahmoud, S.A., 2016. An Enhanced Bag-ofFeatures Framework for Arabic Handwritten Sub-words and Digits Recognition. Journal of Pattern Recognition and Intelligent Systems, 4(1), pp.27-38.

Khorashadizadeh, S. and Latif, A., 2016. Arabic/Farsi Handwritten Digit Recognition using Histogram of Oriented Gradient and Chain Code Histogram. International Arab Journal of Information Technology (IAJIT), 13(4), pp. 1-8.

Naz, S., Ahmed, S.B., Ahmad, R. and Razzak, M.I., 2016. Arabic Script based Digit Recognition Systems. International Conference on Recent Advances in Computer Systems (RACS), pp. 67-73.

Arbain, N.A., Azmi, M.S., Ahmad, S.S.S., Nordin, R., Mas' ud, M.Z. and Lateh, M.A., 2016. Detection on Straight Line Problem in Triangle Geometry Features for Digit Recognition. International Journal on Advanced Science, Engineering and Information Technology, 6(6), pp.1019-1025.

Alwzwazy, H.A., Albehadili, H.M., Alwan, Y.S. and Islam, N.E., 2016. Handwritten Digit Recognition Using Convolutional Neural Networks. International Journal of Innovative Research in Computer and Communication Engineering, 4(2), pp. 1101-1106.

Singh, P.K., Das, S., Sarkar, R. and Nasipuri, M., 2017. Recognition of Handwritten Indic Script Numerals Using Mojette Transform. In Proceedings of the First International Conference on Intelligent Computing and Communication, 458(1), pp. 459-466.

El Hindi, K., Khayyat, M. and Abu Kar, A., 2016. Comparing the machine ability to recognize hand-written Hindu and Arabic digits. Intelligent Automation & Soft Computing, 22(3), pp.1-7.

Boukharouba, A. and Bennia, A., 2015. Novel feature extraction technique for the recognition of handwritten digits. Applied Computing and Informatics. 13(1), pp. 19-26.

Karimi, H., Esfahanimehr, A., Mosleh, M., Salehpour, S. and Medhati, O., 2015. Persian Handwritten Digit Recognition Using Ensemble Classifiers. Procedia Computer Science, 73, pp. 416-425.

El-Sawy, A., Hazem, E.B. and Loey, M., 2016, October. CNN for Handwritten Arabic Digits Recognition Based on LeNet-5. In International Conference on Advanced Intelligent Systems and Informatics,pp. 566-575.

Prasad, B.K. and Sanyal, G., 2016. Novel features and a cascaded classifier based Arabic numerals recognition system. Multidimensional Systems and Signal Processing, 533(1), pp. 1-18.

Fan, J. L., & Zhao, F. (2007). Two-dimensional Otsu's curve thresholding segmentation method for gray-Level images. Dianzi Xuebao(Acta Electronica Sinica), 35(4), 751-755.

Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R news, 2(3), pp. 18-22.

Strobl, C., Malley, J., & Tutz, G. (2009). An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests. Psychological methods, 14(4), pp. 323-348.

Abdelazeem, S., 2009. Comparing arabic and latin handwritten digits recognition problems. World Academy of Science, Engineering and Technology, 3(6), pp. 1583-1587.

Khosravi, H. and Kabir, E., 2007. Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern recognition letters, 28(10), pp. 1133-1141.

Downloads

Published

2017-09-15

How to Cite

M. Alghazo, J., Latif, G., Elhassan, A., Alzubaidi, L., Al-Hmouz, A., & Al-Hmouz, R. (2017). An Online Numeral Recognition System Using Improved Structural Features – A Unified Method for Handwritten Arabic and Persian Numerals. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(2-10), 33–40. Retrieved from https://jtec.utem.edu.my/jtec/article/view/2703