Bulanık kurallara ve kenar devamlılığı kurallarına dayalı kenar tespiti iyileştirilmesi

Öz

Bu çalışmada tuz ve biber gürültüsü eklenmiş gri seviyeli sayısal görüntülerde bulanık kurallara (BK) ve kenar devamlılığı kurallarına (KDK) dayalı kenar tespiti yapılması amaçlanmıştır.  Bu yöntem yüksek gürültü oranlı görüntülerde diğer birçok yöntemden daha iyi sonuç vermektedir. Bulanık üyelikler maksimum entropi değerine göre belirlenmektedir. Görüntünün sinyal gürültü oranı hesaplanmış ve bu orana göre kenar devamlılığı kurallarının durulaştırılması ile bulanık kuralların durulaştırılması arasında seçim yapılmıştır. Parametreye ihtiyaç duymayan bu yöntem Canny, Roberts ve Sobel yöntemleriyle karşılaştırılmıştır.  Kenar devamlılığı kurallarının sürece dâhil edilmediği durumlarda programın çalışma süresinin azaldığı gösterilmiştir.

Anahtar Kelimeler

• Bulanık üyelik,kenar,sinyal gürültü oranı

Improvement of edge detection based on fuzzy rules and edge continuity rules

Öz

In this study it was intended to do edge detection based on fuzzy rules (FR) and edge continuity rules (ECR) in salt and pepper noise added gray level images.  This method has better results than other methods in high level noise ratio images.  Fuzzy memberships are determined according to maximum entropy value.  Image signal to noise ratio has been computed and the choice is made between fuzzy rules defuzzification and edge continuity rules defuzzification according to this ratio.  This method that does not need parameters has been compared with Canny, Roberts and Sobel operators.  It has been shown that program run time decreased in situations that edge continuity rules is not included in the process.

Anahtar Kelimeler

• Fuzzy membership,edge,signal noise ratio

Kaynakça

1. Nallaperumal K., Varghese J., Saudia S., Krishnaveni K., Mathew S.P. ve Kumar P., An efficient Switching Median Filter for Salt Pepper Impulse Noise Reduction, 2006 1st International Conference on Digital Information Management, 161-166, (2007).
2. Hu, L., Cheng, H. D. ve Zang, M., A high performance edge detector based on fuzzy inference rules, An International Journal on Information Sciences, 177, 21, 4768-4784, (2007).
3. Pitas, I. ve Venetsanopou, N., Nonlinear Digital Filters: Principles and Application, 243, Springer, (1990).
4. Premchaiswadi, N., Yimngam S. ve Premchaiswadi, W., A Scheme for Salt and Pepper Noise Reduction on Graylevel and Color Images, Proceedings of the 9th WSEAS International Conference on Signal Processing, Computational Geometry and Artificial Vision, 57-61, (2009).
5. Chinnasarn K., Rangsanseri, Y. ve Thitimajshima, P., Removing salt and pepper noise in text/graphics images, Circuits and Systems, 1998. IEEE APCCAS 1998. The 1998 IEEE Asia-Pacific Conference on, 459-462, (1998). http://web.firat.edu.tr/iaydin/bmu357/bmu357_bolum_5.pdf, (24.03.2017).
6. https://en.wikipedia.org/wiki/Median_filter, (24.03.2017).
7. Changhong W., Taoyi C. ve Zhenshen Q., A novel improved median filter for salt-and-pepper noise from highly corrupted images, 2010 3rd International Symposium on Systems and Control in Aeronautics and Astronautics, 718-722, (2010).
8. Zhou Y., Tang Q.H. ve Jin W.D., Adaptive Fuzzy Median Filter for Images Corrupted by Impulse Noise, 2008 Congress on Image and Signal Processing, 265-269, (2008).

9. Palabaş T. ve Gangal A., Adaptive fuzzy filter combined with median filter for reducing intensive salt and pepper noise in gray level images, 2012 International Symposium on Innovations in Intelligent Systems and Applications, 1-4, (2012).
10. Singh S. ve Singh B., Effects of noise on various edge detection techniques, Computing for Sustainable Global Development (INDIACom), 2015 2nd International Conference, 827-830, New Delhi, (2015). https://tr.wikipedia.org/wiki/Bulanık_mantık, (24.03.2017).
11. Russo F. ve Ramponi G., Edge extraction by FIRE operators, Proceedings of the Third IEEE International Conference on Fuzzy Systems, 249–253, (1994).
12. Shannon C.E., “A mathematical theory of communication,” The Bell System Technical Journal, vol. 27, no. 3, pp. 379–656, (1948).
13. Gonzalez, C.F. veWoods, R. E., Digital Image Processing, 231, Pearson, (2007).
14. Baykal, N. ve Beyan, T., Bulanık mantık ilke ve temelleri, 383-385, Bıçaklar Kitabevi, (2004).
15. Pfluger N., Yen J. ve Langari R., A defuzzification strategy for a fuzzy logic controller employing prohibitive information in command formulation, [1992 Proceedings] IEEE International Conference on Fuzzy Systems, 717-723, San Diego (1992).