Adaptive Threshold Selection of Anisotropic Diffusion Filters Using Dissimilarity Transform

Yıl 2023, Cilt: 15 Sayı: 2, 558 - 573, 14.07.2023

Mahmut Kılıçaslan

https://doi.org/10.29137/umagd.1268609

Öz

One of the most basic steps of image processing is denoising. Diffusion filters have been used for denoising for many years, as they protect the edges. The common problem of diffusion filters, which are still being developed today, is the user intervention requirements. The diffusion threshold value is currently selected by the user. In this study, a fully adaptive threshold value selection method is presented with the help of dissimilarity transform. The main contribution of the study is the proposal of dissimilarity transformation for anisotropic diffusion filters. Experimental results show that the threshold values determined by the proposed method effectively provide denoising without being affected by noise variance and preserve the edges.

Anahtar Kelimeler

Anistropic diffusion filter, Adaptive threshold selection, Dissimilarity Transform, Denoising

Benzemezlik Dönüşümü Kullanarak Anizotropik Difüzyon Filtresinin Uyarlanabilir Eşik Seçimi

Öz

Görüntü işlemenin en temel adımlarından biri gürültü filtreleridir. Difüzyon filtreleri, kenarları koruduklarından dolayı uzun yıllardır gürültü giderme amacıyla kullanılmaktadır. Günümüzde hala geliştirilmekte olan difüzyon filtrelerinin ortak sorunu kullanıcı müdahalesi gereksinimleridir. Difüzyon eşik değerinin belirlenmesi kullanıcı bağımlı bir aşamadır. Bu çalışmada benzemezlik dönüşümü yardımıyla tam uyarlanabilir bir eşik değer seçim yöntemi sunulmaktadır. Çalışmanın temel katkısı, anizotropik difüzyon filtreleri için benzemezlik dönüşümü önerisidir. Deneysel sonuçlar, önerilen yöntemle belirlenen eşik değerlerinin gürültü varyansından etkilenmeden gürültü gidermeyi etkin bir şekilde sağladığını ve kenarları koruduğunu göstermektedir.

Anahtar Kelimeler

Anizotropik difüzyon filtresi, Uyarlanabilir eşik seçimi, Benzemezlik dönüşümü, Gürültü

Kaynakça

• Aja-Fernández, S., & Alberola-López, C. (2006). On the estimation of the coefficient of variation for anisotropic diffusion speckle filtering. IEEE Transactions on Image Processing, 15(9), 2694-2701.
• Ali, H. (2013). Fast Color Edge Detection Algorithm Based on Similarity Relation Matrix. International Journal of Computer Science Issues (IJCSI), 10(5), 108.
• Aydın, M., Hardalaç, F., Ural, B., & Karap, S. (2016). Neonatal jaundice detection system. Journal of medical systems, 40, 1-11.
• Barbu, T. (2016). A hybrid nonlinear fourth-order PDE-based image restoration approach. 2016 20th International Conference on System Theory, Control and Computing (ICSTCC),
• Charbonnier, P., Blanc-Feraud, L., Aubert, G., & Barlaud, M. (1994). Two deterministic half-quadratic regularization algorithms for computed imaging. Proceedings of 1st international conference on image processing,
• Demirci, R. (2007). Similarity relation matrix-based color edge detection. AEU-international Journal of Electronics and Communications, 61(7), 469-477.
• Demirci, R., Guvenc, U., & Tanyeri, U. (2012). Anisotropic diffusion filter without conductivity parameters. 2012 16th International Conference on System Theory, Control and Computing (ICSTCC),
• Demirci, R., & Tanyeri, U. (2012). Anisotropic diffusion filter using Haar wavelet. 2012 16th International Conference on System Theory, Control and Computing (ICSTCC),
• Deng, L., Zhu, H., Yang, Z., & Li, Y. (2019). Hessian matrix-based fourth-order anisotropic diffusion filter for image denoising. Optics & Laser Technology, 110, 184-190.
• Gao, L., Yao, D., Li, Q., Zhuang, L., Zhang, B., & Bioucas-Dias, J. M. (2017). A new low-rank representation based hyperspectral image denoising method for mineral mapping. Remote sensing, 9(11), 1145.
• Guvenc, U., Elmas, C., & Demirci, R. (2008). Automatic Segmentation of Color Images. JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, 11(1), 9-12.
• Hajiaboli, M. R. (2009). A self-governing hybrid model for noise removal. Advances in Image and Video Technology: Third Pacific Rim Symposium, PSIVT 2009, Tokyo, Japan, January 13-16, 2009. Proceedings 3,
• Ham, B., Min, D., & Sohn, K. (2012). Robust scale-space filter using second-order partial differential equations. IEEE Transactions on Image Processing, 21(9), 3937-3951.
• Incelas, M. O., Demirci, R., Yavuzcan, H. G., Tanyeri, U., & Veske, E. (2014). Seeded region growing based detection of cells in fish blood stained with Natt-Herrick. 2014 22nd Signal Processing and Communications Applications Conference (SIU),
• Incetas, M. O., Demirci, R., & Yavuzcan, H. G. (2014). Automatic segmentation of color images with transitive closure. AEU-international Journal of Electronics and Communications, 68(3), 260-269.
• INCETAS, M. O., Demirci, R., & YAVUZCAN, H. G. (2019). Automatic color edge detection with similarity transformation. Gazi University Journal of Science, 32(2), 458-469.
• İncetaş, Tanyeri, U., Kılıçaslan, M., Yakışır Girgin, B., & Demirci, R. (2017). Eşik Seçiminin Benzerliğe Dayalı Kenar Belirlemeye Etkisi. 1st International Symposium on Multidisciplinary Studies and Innovative Technologies, Tokat/Turkey.
• İncetaş, M. O., & Uçar, M. (2021, 16-18 May). İğnecikli sinir ağina dayali benzerlik dönüşümü ISPEC 10th INTERNATIONAL CONFERENCE ON ENGINEERING & NATURAL SCIENCES, Siirt/Turkey.
• İncetaş, M. O., VESKE, E., Nesrin, E., & DEMİRCİ, R. (2017). Automatic cells counting in Natt-Herrick stained fish blood. Aquaculture Studies, 17(3), 283-294.
• Jain, P., & Tyagi, V. (2016). A survey of edge-preserving image denoising methods. Information Systems Frontiers, 18, 159-170.
• Perona, P., & Malik, J. (1990). Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on pattern analysis and machine intelligence, 12(7), 629-639.
• Rafsanjani, H. K., Sedaaghi, M. H., & Saryazdi, S. (2016). Efficient diffusion coefficient for image denoising. Computers & Mathematics with Applications, 72(4), 893-903.
• Rafsanjani, H. K., Sedaaghi, M. H., & Saryazdi, S. (2017). An adaptive diffusion coefficient selection for image denoising. Digital Signal Processing, 64, 71-82.
• Tanyeri, U., & Demirci, R. (2018). Wavelet-based adaptive anisotropic diffusion filter. Advances in Electrical and Computer Engineering, 18(4), 99-106.
• Tsiotsios, C., & Petrou, M. (2013). On the choice of the parameters for anisotropic diffusion in image processing. Pattern Recognition, 46(5), 1369-1381.
• Türk, F., Lüy, M., & Barışçı, N. (2020). Kidney and renal tumor segmentation using a hybrid V-Net-based model. Mathematics, 8(10), 1772.
• Türk, F., Murat, L., & BARIŞÇI, N. (2019). Machine learning of kidney tumors and diagnosis and classification by deep learning methods. International Journal of Engineering Research and Development, 11(3), 802-812.
• Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600-612.
• Weickert, J. (1998). Anisotropic diffusion in image processing (Vol. 1). Teubner Stuttgart.
• Xu, J., Jia, Y., Shi, Z., & Pang, K. (2016). An improved anisotropic diffusion filter with semi-adaptive threshold for edge preservation. Signal Processing, 119, 80-91.
• You, Y.-L., & Kaveh, M. (2000). Fourth-order partial differential equations for noise removal. IEEE Transactions on Image Processing, 9(10), 1723-1730.
• Yu, J., Tan, J., & Wang, Y. (2010). Ultrasound speckle reduction by a SUSAN-controlled anisotropic diffusion method. Pattern Recognition, 43(9), 3083-3092.