A NEURO-FUZZY GRAPHIC OBJECT CLASSIFIER WITH MODIFIED DISTANCE MEASURE ESTIMATOR

Document Type: Research Paper

Authors

1 MEMBER IEEE, DEPARTMENT OF COMPUTER-AIDED CONTROL SYSTEMS, AZERBAIJAN STATE OIL ACADEMY, BAKU, AZERBAIJAN

2 DEPARTMENT OF COMPUTER-AIDED CONTROL SYSTEMS, AZERBAIJAN STATE OIL ACADEMY, BAKU, AZERBAIJAN

3 EASTERN MEDITERRANEAN UNIVERSITY, NORTH CYPRUS

Abstract

The paper analyses issues leading to errors in graphic object classifiers. The
distance measures suggested in literature and used as a basis in traditional, fuzzy, and
Neuro-Fuzzy classifiers are found to be not suitable for classification of non-stylized or
fuzzy objects in which the features of classes are much more difficult to recognize because
of significant uncertainties in their location and gray-levels. The authors suggest a neurofuzzy
graphic object classifier with modified distance measure that gives better
performance indices than systems based on traditional ordinary and cumulative distance
measures. Simulation has shown that the quality of recognition significantly improves
when using the suggested method.

Keywords


[1] J. Bezdek and S. Pal (ed.), Fuzzy models for pattern recognition, New York: IEEE Press (1992).
[2] X. Ye, C.Suen and M.Cheriet, A generic system to extract and clean handwritten data from business
forms, in Prof. Int. Workshop on Frontiers in handwriting Recognition, Amsterdam (2000) 63-72.
[3] R. A. Aliev and R. R. Aliev, Soft Computing and its applications, World Scientific Publishing Co.
Pte. Ltd (2001) p. 444.
[4] K. Saastamoinen, V. Könönen, and P. Luukka, A classifier based on the fuzzy similarity in the
Lukasiewicz structure with different metrics, in proceedings of IEEE International Conference on
Fuzzy Systems, FUZZ-IEEE’02, Vol. 1 (2002) 363-367.
[5] H. Bandemer and W. Näther, Fuzzy data analysis, Theory and Decision Library, Series B:
Mathematical and Statistical Methods, Vol. 20, Cluwer Academic Publishers (1992) 67-71.
[6] L. Mascarilla and C. Frélicot, Combining rejection-based pattern classifiers, in 19th International
Conference of the North American Fuzzy Information Processing Society – NAFIPS, PeachFuzz
2000 (2000) 114-118.
[7] R Aliev and B. Guirimov, Handwritten image recognition by using neural and fuzzy approaches,
Intelligent Control and Decision Making Systems, No. 1, Thematic Collected Articles, Baku,
Publishing House of Azerb. State Oil Academy (1997) 3-7.
[8] R. Aliev, B. Guirimov, K. Bonfig, and Steinmann, A neuro-fuzzy algorithm for recognition of nonstylized
images, in proceedings of Fourth International Conference on Application of Fuzzy
Systems and Soft Computing, ICAFS’2000, Siegen, Germany (2000) 238-241.
[9] S. Halgamuge and M. Glesner, A fuzzy neural approach for pattern classification with generation of
rules based on supervised learning, in proceedings of Nuro Nimes 92 (1992) 165-173.
[10] V. Uebele, S. Abe, and M. Lan, A neural - network based fuzzy classifier, IEEE Transactions on
Systems, Man, and Cybernetics, Vol. 23, No. 3 (1995) 353-361.
[11] R. Yager, A general approach to rule aggregation in fuzzy logic control, Appl. Intelligence, 2
(1992) 333-351. [12] R. Yager, On a general class of fuzzy connectives, Fuzzy Sets and Systems, 4 (1980) 235-242.