In this paper we present a novel fuzzy technique for Arabic (Indian) online digits recognition. We use directional features to automatically build generic fuzzy models for Arabic online digits using the training data. The fuzzy models include the samples’ trend lines, the upper and lower envelops of the samples of each digit. Automatically generated weights for the different segments of the digits’ models are also used. In addition, the fuzzy intervals are automatically estimated using the training data. The fuzzy models produce robust models that can handle the variability in the handwriting styles. The classification phase consists of two cascaded stages, in the first stage the system classifies digits into zero/nonzero classes using five features (viz. length, width, height, height’s variance and aspect ratio) and the second stage classifies digits 1 to 9 using fuzzy classification based on directional and segment histogram features. Support Vector Machine (SVM) is used in the first stage and syntactic fuzzy classifier in the second stage. A database containing 32695 Arabic online digits is used in the experimentation. The results show that the first stage (zero/nonzero) achieved accuracy of 99.55% and the second stage (digits from 1 to 9) achieved accuracy of 98.01%. The misclassified samples are evaluated subjectively and results indicate that humans could not classify  35% of the misclassified digits.

[1] Abdelazeem S. and El-Sherif E., “Arabic Handwritten Digit Recognition,” International Journal of Document Analysis and Recognition, vol. 11, no. 3, pp. 127-141, 2008.

[2] Abdelazeem S., El Meseery M., and Ahmed H., “Online Arabic Handwritten Digits Recognition,” in Proceeding of International Conference on Frontiers in Handwriting Recognition, Bari, pp. 135-140, 2012.

[3] Abuhaiba S., Mahmoud S., and Green R., “Recognition of Handwritten Cursive Arabic characters,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 6, pp. 664-672, 1994.

[4] Abuzaraida M. and Zeki A., “Feature Extraction Techniques of Online Handwriting Arabic Text Recognition,” in Proceeding of 5th International Conference on Information and Communication Technology for the Muslim World, Rabat, pp. 1-7, 2013.

[5] AlKhateeb J. and Alseid M., “DBN-Based Learning For Arabic Handwritten Digit Recognition Using DCT Features,” in Proceeding of 6th International Conference on Computer Science and Information Technology, Amman, pp. 222- 226, 2014.

[6] Al-Taani A. and Al-Haj S., “Recognition of On-line Arabic Handwritten Characters Using Structural Features,” Journal of Pattern Recognition Research, vol. 5, no. 1, pp. 23-37, 2010.

[7] Beigi H., Nathan K., Clary G., and Subrahmonia J., “Challenges of Handwriting Recognition in Farsi, Arabic and Other Languages with Similar Writing Styles (An On- line Digit Recognizer),” in Proceeding of the 2nd Annual Conference on Technological Advancements in Developing Countries, New York, 1994.

[8] Douglas D. and Peucker T., “Algorithms for The Reduction of the Number of Points Required to Represent A Digitized Line or its Caricature,” Cartographica: The International Journal for Geographic Information and Geovisualization vol. 10, no. 2, pp. 112-122, 1973.

[9] Duong A., Phan H., Le N., and Tran S., “A Hierarchical Approach for Handwritten Digit Recognition Using Sparse Autoencoder,” Issues and Challenges of Intelligent Systems and Computational Intelligence, Springer International Publishing, 2014.

[10] Halawani K., “Arabic Online Text Recognition using Syntactic (Structural) Approach,” M.S. Thesis, King Fahd University of Petroleum and Minerals, 2013.

[11] Impedovo S., Mangini F., and Barbuzzi D., “A Novel Prototype Generation Technique for Handwriting Digit Recognition,” Pattern Recognition, vol. 47, no. 3, pp. 1002-1010, 2014.

[12] Jiang W., Sun Z., Yuan B., Zheng W., and Xu W., “User-Independent Online Handwritten Digit Recognition,” in Proceeding of International Conference on Machine Learning and Cybernetics, Dalian, pp. 3359-3364, 2006.

[13] Kherallah M., Njah S., Alimi A., and Derbel N., “Recognition of On-Line Handwritten Digits by Neural Networks Using Circular and Beta Approaches,” in Proceeding of IEEE International Conference on Systems, Man and Cybernetics, Tunisia, pp. 164-169, 2002.

[14] Kherallah M., Alimi A., and Derbel N., “On-Line Recognition of Handwritten digits by “Self Organisation Maps” Using Elliptical and Beta Representations,” in Proceeding of First International Congress on Signals, Circuits and Systems, Monastir, pp. 503-507, 2004.

[15] Kherallah M., Haddad L., Alimi A., and Mitiche A., “On-Line Handwritten Digit Recognition Based on Trajectory and Velocity Modeling,” Pattern Recognition Letters, vol. 29, no. 5, pp. 580-594, 2008.

[16] Khorashadizadeh S. and Latif A., “Arabic/Farsi Handwritten Digit Recognition using Histogram of Oriented Gradient and Chain Code Histogram,” The International Arab Journal of Information Technology, vol. 13, no. 4, pp. 367-374, 2016.

[17] Mahmoud S., “Arabic (Indian) Handwritten Digits Recognition Using Gabor-Based Features,” in Proceeding of International Conference on Innovations in Information Technology, Al Ain, pp. 683-687, 2008.

[18] Mahmoud S., “Recognition Of Writer- Independent Off-Line Handwritten Arabic (Indian) Numerals Using Hidden Markov Models,” Signal Processing, vol. 88, no. 4, pp. 844-857, 2008.

[19] Mahmoud S. and Al-Khatib W., “Recognition Of Arabic (Indian) Bank Check Digits Using Log- Gabor Filters,” Applied Intelligence, vol. 35, no. 3, p p . 445-456, 2011.

[20] Niu X. and Suen C., “A Novel Hybrid CNN-SVM Classifier For Recognizing Handwritten Digits,” Pattern Recognition, vol. 45, no. 4, pp. 1318-1325, 2012.

[21] Parvez M. and Mahmoud S., “Offline Arabic Fuzzy Modeling for Handwritten Arabic Numeral Recognition 511 Handwritten Text Recognition: A Survey,” ACM Computing Surveys, vol. 45, no. 2, pp. 1-35, 2013.

[22] Parvez M. and Mahmoud S., “Arabic Handwriting Recognition Using Structural and Syntactic Pattern Attributes,” Pattern Recognition, vol. 46, no. 1, pp. 141-154, 2013.

[23] Plamondon R. and Srihari S., “Online and Off- Line Handwriting Recognition: A Comprehensive Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 63-84, 2000.

[24] Subhashini P. and Prasad V., “Recognition of Handwritten Digits Using Rbf Neural Network,” International Journal of Research in Engineering and Technology, vol. 2, no. 3, pp. 393-397, 2013.

[25] Teredesai A., Ratzlaff E., Subrahmonia J., and Govindaraju V., “On-Line Digit Recognition Using Off-Line Features,” in Proceeding of Indian Conference on Computer Vision, Graphics and Image Processing, Ahmadabad, 2002. Dhiaa Musleh received his B.Sc. in Computer Science from Mosul University, Iraq, and then he joined the faculty of applied science at Taiz University as a teaching assistance. He received his.S. in Computer Science from King Fahd University of Petroleum and Minerals (KFUPM),Saudi Arabia; he is currently a PhD candidate at the Information and Computer Science Department at KFUPM. His research interests include pattern recognition, Arabic document analysis and recognition. Khaldoun Halawani received his B.Sc. degree in Information Technology form Palestine Polytechnic University (PPU), Palestine. And his M.Sc. degree in Information and Computer Sciences from King Fahd University of Petroleum and Minerals (KFUPM), Kingdome of Saudi Arabia, in 2009 and 2013, respectively. His research work and interests are on machine learning, pattern recognition, multimedia processing and artificial intelligence. He worked for four years as research assistance in PPU and KFUPM. Sabri Mahmoud is a Professor of computer Science in the ICS Department, KFUPM. His research interests include Arabic Document Analysis and Recognition, Arabic NLP, Image Analysis and applications of Pattern Recognition. Dr. Mahmoud is a life senior member of IEEE. He published over 80 papers in refereed journals and conference proceedings.