Klasik ve Bulanık Kenar Algılama Yöntemlerinin Karşılaştırılması

Abstract

Görüntü işlemedeki zorlu problemlerden biri kenar algılamadır. Bu çalışmada, literatürden Sobel, Prewitt, Roberts ve Canny olmak üzere dört farklı klasik kenar algılama yöntemi ile tip-1 bulanık çıkarım ve tip-2 bulanık çıkarım olan iki bulanık mantık tabanlı kenar algılama yöntemi iki farklı veri kümesine uygulanmıştır. Veri setlerinden biri retina görüntüleri olan STARE, diğeri ise sokak görüntülerini içeren BIPED veri setidir. Her yöntemin simülasyon sonuçları üç farklı hata metrikleri kullanılarak karşılaştırılmıştır. Bunlar Tepe Sinyal Gürültü Oranı (PSNR), Yapısal Benzerlik Endeksi (SSIM) ve Ortalama Karesel Hata’dır (MSE). Şu sonuca vardık; tip-2 bulanık yöntem kan damarı tespiti için tıbbi görüntüler için en iyisidir ve sokak görüntülerinde de kullanılabilir, daha genel görüntüler için tip-1 bulanık yöntem seçilebilir ve PSNR metriği açısından daha genel görüntüler için Roberts en iyisidir ancak bizim fikrimize göre tip-1 bulanık yöntemin sonucu görsel olarak daha tatmin edicidir.

Keywords

• Bulanık çıkarım sistemi
• Tip-1 bulanık çıkarım sistemi
• Tip-2 bulanık çıkarım sistemi
• Kenar algılama
• Görüntü işleme

COMPARISON OF CLASSICAL AND FUZZY EDGE DETECTION METHODS

Abstract

Edge detection is one of the challenging problems in image processing. Four different classical edge detection methods—Sobel, Prewitt, Roberts, and Canny—and type-1 and type-2 fuzzy logic-based edge detection methods are applied to analyze two separate datasets with various properties. The datasets are STARE which contains medical images of the retina and BIPED which contains images of the street. Furthermore, two separate hybrid fuzzy logic methods are implemented. The type-1 and type-2 fuzzy inference techniques are combined to produce the hybrid-1 and hybrid-2 approaches, using the "AND" and "OR" logic operators. We compare the simulation results for each technique using three different image quality metrics. These are Mean Square Error (MSE), Peak Signal Noise Ratio (PSNR), and Structural Similarity Index (SSIM). The type-2 fuzzy technique outperformed the hybrid-1 fuzzy method in visual quality metrics comparison, demonstrating superior blood vessel recognition on the STARE retinal image dataset—a dataset that more closely resembles the human visual system. Using the BIPED street image dataset, the hybrid-1 fuzzy approach outperformed the Roberts method. The hybrid-1 fuzzy technique showed good results in the second order for both kinds of datasets. Any data and general applications can take advantage of it.

Keywords

• Edge detection
• Fuzzy inference system
• Hybrid fuzzy inference system
• Image processing
• Type-1 fuzzy inference system
• Type-2 fuzzy inference system

References

1. S. Yunhong, Y. Shilei, Z. Xiaojing, and Y. Jinhua, “Edge Detection Algorithm of MRI Medical Image Based on Artificial Neural Network,” in Procedia Computer Science, Elsevier B.V., 2022, pp. 136–144. doi: 10.1016/j.procs.2022.10.021.
2. M. C. Shin, D. B. Goldgof, and K. W. Bowyer, “Comparison of edge detector performance through use in an object recognition task,” Computer Vision and Image Understanding, vol. 84, no. 1, pp. 160–178, 2001, doi: 10.1006/cviu.2001.0932.
3. C. I. Gonzalez, P. Melin, and O. Castillo, “Edge detection method based on general type-2 fuzzy logic applied to color images,” Information (Switzerland), vol. 8, no. 3, Aug. 2017, doi: 10.3390/info8030104.
4. P. Melin, O. Mendoza, and O. Castillo, “An improved method for edge detection based on interval type-2 fuzzy logic,” Expert Syst Appl, vol. 37, no. 12, pp. 8527–8535, 2010, doi: 10.1016/j.eswa.2010.05.023.
5. Y. Becerikli and T. M. Karan, “LNCS 3512 - A New Fuzzy Approach for Edge Detection,” in LNCS, Springer-Verlag, 2005, pp. 943–951.
6. L. Hu, H. D. Cheng, and M. Zhang, “A high performance edge detector based on fuzzy inference rules,” Inf Sci (N Y), vol. 177, no. 21, pp. 4768–4784, Nov. 2007, doi: 10.1016/j.ins.2007.04.001.
7. M. E. Yüksel, “Edge detection in noisy images by neuro-fuzzy processing,” AEU - International Journal of Electronics and Communications, vol. 61, no. 2, pp. 82–89, Feb. 2007, doi: 10.1016/j.aeue.2006.02.006.
8. C. C. Kang and W. J. Wang, “A novel edge detection method based on the maximizing objective function,” Pattern Recognit, vol. 40, no. 2, pp. 609–618, Feb. 2007, doi: 10.1016/j.patcog.2006.03.016.

9. O. Mendoza, P. Melin, and G. Licea, “A New Method for Edge Detection in Image Processing Using Interval Type-2 Fuzzy Logic,” Institute of Electrical and Electronics Engineers (IEEE), Apr. 2008, pp. 151–151. doi: 10.1109/grc.2007.115.
10. F. Jacquey, F. Comby, and O. Strauss, “Fuzzy edge detection for omnidirectional images,” Fuzzy Sets Syst, vol. 159, no. 15, pp. 1991–2010, Aug. 2008, doi: 10.1016/j.fss.2008.02.022.
11. N. Mathur, S. Mathur, and D. Mathur, “A Novel Approach to Improve Sobel Edge Detector,” in Procedia Computer Science, Elsevier B.V., 2016, pp. 431–438. doi: 10.1016/j.procs.2016.07.230.
12. F. Orujov, R. Maskeliūnas, R. Damaševičius, and W. Wei, “Fuzzy based image edge detection algorithm for blood vessel detection in retinal images,” Applied Soft Computing Journal, vol. 94, Sep. 2020, doi: 10.1016/j.asoc.2020.106452.
13. Z. Wang and A. C. Bovik, “Mean squared error: Lot it or leave it? A new look at signal fidelity measures,” IEEE Signal Process Mag, vol. 26, no. 1, pp. 98–117, 2009, doi: 10.1109/MSP.2008.930649.
14. J. Erfurt, C. R. Helmrich, S. Bosse, H. Schwarz, D. Marpe, and T. Wiegand, “A Study of The Perceptually Weighted Peak Signal-To-Noise Ratio (Wpsnr) For Image Compression,” in 2019 IEEE International Conference on Image Processing (ICIP) : September 22-25, 2019, Taipei International Convention Center (TICC), Taipei, Taiwan, IEEE Signal Processing Society, 2019.
15. Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, Apr. 2004, doi: 10.1109/TIP.2003.819861.
16. R. Sun et al., “Survey of Image Edge Detection,” Frontiers in Signal Processing, vol. 2, Mar. 2022, doi: 10.3389/frsip.2022.826967.
17. D. Ziou and S. Tabbone, “Edge detection techniques: An overview’ Article ·,” 1998. [Online]. Available: https://www.researchgate.net/publication/312890367
18. G. T. Shrivakshan and C. Chandrasekar, “A Comparison of various Edge Detection Techniques used in Image Processing,” 2012. [Online]. Available: www.IJCSI.org
19. D. Ma, “Theory of edge detection,” 1980. [Online]. Available: https://royalsocietypublishing.org/
20. X. Wang, “Laplacian operator-based edge detectors,” IEEE Trans Pattern Anal Mach Intell, vol. 29, no. 5, pp. 886–890, May 2007, doi: 10.1109/TPAMI.2007.1027.
21. J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans Pattern Anal Mach Intell, no. 6, 1986.
22. A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating Blood Vessels in Retinal Images by Piecewise Threshold Probing of a Matched Filter Response,” IEEE Trans Med Imaging, vol. 19, no. 3, 2000.
23. X. Soria, E. Riba, and A. Sappa, “Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection.” [Online]. Available: https://github.com/xavysp/DexiNed