Improving Recognition Rate of Persian Handwritten Digits Using FCM Clustering and Inclined Planes System Optimization Algorithm

Najme Ghanbari


In this paper, a method is proposed to increase the recognition rate of the Persian handwritten digits classifier. A fuzzy method is used for classification in which there is just one fuzzy rule for each digit [1]. The number of Persian digits is 10, Therefore, the total number of fuzzy rules used in the base method is 10. After implementation, Where the number of fuzzy rules is ten, the recognition rate is 86.21 and 80.19 percent for training and testing samples, respectively. Clustering is used to increase the recognition rate. Training data related to each digit are divided into several clusters and one fuzzy rule is extracted for each cluster. Thus, the number of fuzzy rules is significantly increased (784 rules), since the recognition rate is also increased significantly, increase of fuzzy rules is acceptable. By applying this method, the recognition rate of training and testing samples is increased to 98.97 and 97.15 percent, respectively. FCM method is used for clustering. To select the optimal number of clusters for each digit, the inclined planes system optimization algorithm is used.


Digits Recognition; FCM Clustering; Inclined Planes System Optimization (IPO); Persian Handwritten Digits;

Full Text:



V. Johari Majd, S. M. Razavi,” Fuzzy recognition of Persian Handwritten Digits”, First Iranian Conference on Machine Vision and Image Processing, 2000, pp. 144-151.

S. M. Razavi, E. A. Kabir, “Persian Separate Letters Online Recognition with Neural Network”, Third Iranian Conference on Machine Vision and Image Processing, 2004, pp. 84-89.

M. Nahvi, M. Rafiee, R. Ebrahim pour, E. A. Kabir, “Combination of Two-Class Classifiers for Recognition of Persian Handwritten Digits” Sixteenth Conference on Electrical Engineering, 2008.

H. Khosravi, “Recognition of Persian Handwritten Letters and Digits in MA National Exam Registration Forms”, Electronic MA thesis, Tarbiat Modarres University, 2005.

A. Darvish, E. A. Kabir, H. Khosravi, “Application of Shape Matching in Persian Handwritten Digits Recognition”, Journal of SID, Issue 22, December 2005.

S. M. Razavi, H. Sadughi Yazdi, E. A. Kabir, “Selecting Feature for Persian Handwritten Digits Recognition by genetic algorithms”, Seventh Annual Conference of Computer Society of Iran, 2001, PP. 285-292.

E. Rashedi, H. NezamAbadi pour, Tohidi, “Feature Selection by using Gravitational Search Algorithm”, Third International Conference of Knowledge and Information Technology, November 27-29, 2007.

H. Z. Nafisi, E. A. Kabir, “Recognition of Persian Handwritten Digits”. Second Conference on Electrical Engineering, 1994, pp.295- 304.

H. Soltanianzadeh, M. Rahmati, “Recognition of Persian handwritten digits using image profiles of multiple orientations”, 25 (2004), Pattern recognition letters, 1569-1576.

M. Sadighi Nav, A. Soleimani Eivari, H. Khosravi, "Feature reduction by Binary Particle Swarm Optimization for handwritten Farsi digit recognition", Journal of Intelligent Systems in Electrical Engineering, 2014, 5: 1.

S. Karimzadeh Bejestani, A. Mohammadi Anbaran, "Recognition of Farsi handwritten digits using SVM", Scientific Journal of Computer Science Research, 2, 2016, pp. 29-36.

N. Ghanbari, S. M. Razavi, S. H. Nabavi Kerizi, "An intelligent feature selection method based on Binary Gravitational Search Algorithm in the handwritten Farsi digit recognition system", Iranian Journal of Electrical and Computer Engineering, 9: 1, 2011.

M. Mozaffari, H. Abdi, S. H. Zahiri, “New Inclined Planes system Optimization (IPO) algorithm”, Journal of Soft Computing and Information Technology, Volume 1, Number 1, Noshirvani University of Technology, Babol, 2012.

N. Langari, M. AbdulRazagh Nejad, “Identifying phishing website in online banking using Inclined Planes Optimization (IPO) algorithm”, Journal of Electronic and Cyber defense, third year, Issue 1, April, 2015, pp.29-40.

A. Mohammadi, S. H. Zahiri, " IIR model identification using a modified inclined planes system optimization algorithm ", Artificial Intelligence Review, 2016.

R. Khosravi, E. A. Kabir, " Introducing a very large dataset of handwritten Farsi digits and a study on their varienties ", Pattern recognition letters, 2007, pp. 1133-114.

M. S. Ghasemi, M. Khangladi, “Application of Fuzzy Logic in Pattern Recognition: Clustering” , Faculty of Engineering, University of Arak, 2009.

M. Yaghini, M. Ranjpour, F. Yousefi, “A Review of Fuzzy Clustering Algorithms” , Third Iranian Data Mining Conference, Tehran, 2009.

E. Alpaydin, " Introduction to Machine Learning ", The MIT Press, 2004.

J. Ghasemi, M. R. Karami Mollaei, R. Ghaderi, A. Hojjatoleslami, " Brain tissue segmentation based on spatial information fusion by Dempster-Shafer theory ", Journal of Zhejiang University SCIENCE, 2012, pp. 520-533.

R. Aian Zadeh, H. Gheybi, Y. Moghadas, K. Hassani, ”Combination of Genetic and Fuzzy Clustering Algorithms using an Innovative Heuristic for Classification of Satellite Images”, Fifth National Conference on Science.

D. H. Rouvary, " Fuzzy Logic In Chemistry ", Academic Press San Diego, 1997.

E. Rashedi, H. Nezamabadi-pour, S. Saryazdi, " GSA: A Gravitational Search Algorithm ", Information Sciences, Vol. 179, No. 13, 2009, pp. 2232-2248.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN: 2180-1843

eISSN: 2289-8131