Çok Seviyeli Görüntü Eşikleme Problemini Çözmek İçin Harmoni Aramalı Yeni Bir Hibrit Gri Kurt Optimizasyon Algoritması

Year 2023, Volume: 5 Issue: 2, 230 - 245, 31.12.2023

Alper Ünlü İlhan İlhan

https://doi.org/10.47112/neufmbd.2023.21

Abstract

Çok seviyeli görüntü eşikleme, görüntüyü ileri düzeyde anlamlı özelliklere ayırmak için kullanılan önemli bir görüntü işleme tekniğidir. Bu teknik, metasezgisel optimizasyon algoritmaları ile birlikte kullanılarak hesaplama süresi açısından başarılı sonuçlar elde edilebilmektedir. Bu çalışmada, çok seviyeli görüntü eşikleme problemini çözmek için GWO-HS olarak isimlendirilen hibrit bir algoritma önerilmiştir. Önerilen algoritma gri kurt optimizasyon (GWO) ve harmoni arama (HS) algoritmaları hibritlenerek elde edilmiştir. GWO-HS algoritmasının performansı beş diğer algoritmanın performansları ile karşılaştırılmıştır. Karşılaştırmalarda Otsu ve Kapur entropi tabanlı eşikleme yöntemleri kullanılmıştır. Deneylerde, görüntü işleme çalışmalarında iyi bilinen ve yaygın olarak kullanılan altı görüntü tercih edilmiştir. Her bir görüntü üzerinde 2’den 10’a kadar değişen seviyeler için eşikleme işlemi uygulanmıştır. Sonuçlar, önerilen GWO-HS algoritmasının, diğer algoritmalara kıyasla özellikle yüksek eşik seviyeleri için daha üstün bir performansa sahip olduğunu göstermiştir.

Keywords

Gri Kurt Optimizasyon, Harmoni arama, Kapur, Çok seviyeli görüntü eşikleme, Otsu.

A Novel Hybrid Gray Wolf Optimization Algorithm with Harmony Search to Solve Multi-Level Image Thresholding Problem

Abstract

Multi-level image thresholding is an important image processing technique used to separate an image into advanced meaningful features. By using this technique together with metaheuristic optimization algorithms, successful results can be achieved in terms of computational time. In this study, a hybrid algorithm called GWO-HS was proposed to solve the multi-level image thresholding problem. The proposed algorithm was obtained by hybridizing the Gray Wolf Optimization (GWO) and Harmony Search (HS) algorithms. The performance of the GWO-HS algorithm was compared with the performances of five other algorithms. Otsu and Kapur entropy-based thresholding methods were used in the comparisons. In the experiments, six images, which are well known and widely used in image processing studies, were preferred. Thresholding was applied for threshold levels ranging from 2 to 10 on each image. The results showed that the proposed GWO-HS algorithm has superior performance compared to other algorithms, especially for high threshold levels.

Keywords

Grey wolf optimization, Harmony search, Kapur, Multilevel image thresholding, Otsu.

References

• J. Lázaro, J. L. Martín, J. Arias, A. Astarloa, C. Cuadrado, Neuro semantic thresholding using OCR software for high precision OCR applications, Image and Vision Computing. 28(4) (2010), 571-578. doi:10.1016/j.imavis.2009.09.011.
• G. C. Anagnostopoulos, SVM-based target recognition from synthetic aperture radar images using target region outline descriptors, Nonlinear Analysis: Theory, Methods & Applications. 71(12) (2009), 2934-2939. doi:10.1016/j.na.2009.07.030.
• Y. T. Hsiao, C. L. Chuang, Y. L. Lu, J. A. Jiang, Robust multiple objects tracking using image segmentation and trajectory estimation scheme in video frames, Image and Vision Computing. 24(10) (2006), 1123-1136. doi:10.1016/j.imavis.2006.04.002.
• S. Ayas, H. Dogan, E. Gedikli, M. Ekinci, Microscopic image segmentation based on firefly algorithm for detection of tuberculosis bacteria, 23rd Signal Processing and Communications Applications Conference, IEEE, 2015, 851-854. doi:10.1109/SIU.2015.7129962.
• A. Tabak, İ. İlhan, An effective method based on simulated annealing for automatic generation control of power systems, Applied Soft Computing. 126 (2022), 109277. doi:10.1016/j.asoc.2022.109277.
• İ. İlhan, An improved simulated annealing algorithm with crossover operator for capacitated vehicle routing problem, Swarm and Evolutionary Computation. 64 (2021), 100911. doi: 10.1016/j.swevo.2021.100911.
• M. Karakoyun, A. Özkış, Development of Binary Moth-Flame Optimization Algorithms using Transfer Functions and Their Performance Comparison. Necmettin Erbakan University Journal of Science and Engineering. 3(2) (2021), 1-10. doi: 10.47112/neufmbd.2021.7.
• A. Pektaş, O. İnan, Application of Tree Seed Algorithm on Clustering Problems, Necmettin Erbakan University Journal of Science and Engineering. 4(1) (2022). 1-10. doi: 10.47112/neufmbd.2022.8.
• O. Banimelhem, Y. A. Yahya, Multi-thresholding image segmentation using genetic algorithm, The International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV), 2011, 1.
• A. Alihodzic, M. Tuba, Improved bat algorithm applied to multilevel image thresholding, The Scientific World Journal. (2014), 2014, doi: 10.1155/2014/176718.
• I. Brajevic, M. Tuba, Cuckoo search and firefly algorithm applied to multilevel image thresholding, Studies in Computational Intelligence. 516 (2014), 115-139. doi: 10.1007/978-3-319-02141-6_6.
• V. Rajinikanth, N. S. M. Raja, K. Kamalanand, Firefly algorithm assisted segmentation of tumor from brain MRI using Tsallis function and Markov Random Field, Journal of Control Engineering and Applied Informatics. 19(3) (2017), 97-106.
• F. Huo, X. Sun, W. Ren, Multilevel image threshold segmentation using an improved Bloch quantum artificial bee colony algorithm, Multimedia Tools and Applications. 79(3-4) (2020), 2447-2471. doi: 10.1007/S11042-019-08231-7.
• M. H. Mozaffari, W. S. Lee, Convergent heterogeneous particle swarm optimisation algorithm for multilevel image thresholding segmentation, IET Image Processing. 11(8) (2017), 605-619. doi: 10.1049/iet-ipr.2016.0489.
• N. Muangkote, K. Sunat, S. Chiewchanwattana, Rr-cr-IJADE: An efficient differential evolution algorithm for multilevel image thresholding, Expert Systems with Applications. 90 (2017), 272-289. doi: 10.1016/j.eswa.2017.08.029.
• N. G. Şengöz, F. Zeybek, Sharp Silhouettes for Obtaining 3D Body Measurements from 2D Images, Necmettin Erbakan University Journal of Science and Engineering. 4(2) (2022), 8-25. doi: 10.47112/neufmbd.2022.2.
• S. Arora, J. Acharya, A. Verma, P. K. Panigrahi, Multilevel thresholding for image segmentation through a fast statistical recursive algorithm, Pattern Recognition Letters. 29(2) (2008), 119-125. doi: doi:10.1016/j.patrec.2007.09.005.
• N. Otsu, A threshold selection method from gray-level histograms, IEEE Transactions on Systems, Man, and Cybernetics. 9(1) (1979), 62-66.
• J. N. Kapur, P. K. Sahoo, A. K. C. Wong, A new method for gray-level picture thresholding using the entropy of the histogram, Computer Vision, Graphics, and İmage Processing. 29(3) (1985), 273-285. doi: 10.1016/0734-189X(85)90125-2.
• I. Koc, O. K. Baykan, I. Babaoglu, Multilevel image thresholding selection based on grey wolf optimizer, Journal of Polytechnic. 21(4), 2018, 841-847. doi:10.2339/politeknik.389613.
• S. Mirjalili, S. M. Mirjalili, A. Lewis, Grey Wolf Optimizer, Advances in Engineering Software. 69 (2014), 46-61. doi:10.1016/j.advengsoft.2013.12.007.
• Z. W. Geem, J. H. Kim, G. V. Loganathan, A New Heuristic Optimization Algorithm: Harmony Search, Simulation. 76(2) (2001), 60-68. doi: 10.1177/003754970107600201.