Multilevel thresholding segmentation of color plant disease images using metaheuristic optimization algorithms


AKAY R., Saleh R. A. A., Farea S. M. O., KANAAN M.

Neural Computing and Applications, cilt.34, sa.2, ss.1161-1179, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 34 Sayı: 2
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s00521-021-06437-1
  • Dergi Adı: Neural Computing and Applications
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, Biotechnology Research Abstracts, Compendex, Computer & Applied Sciences, Index Islamicus, INSPEC, zbMATH
  • Sayfa Sayıları: ss.1161-1179
  • Anahtar Kelimeler: Multilevel thresholding segmentation, Metaheuristic optimization, Teaching-learning-based artificial bee colony, Plant disease, ENTROPY
  • Kayseri Üniversitesi Adresli: Hayır

Özet

© 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.In this study, we apply multilevel thresholding segmentation to color images of plant disease. Given that thresholding segmentation is just an optimization problem, we use Otsu’s function as the objective function. To solve this optimization problem, we implement five metaheuristic algorithms, namely artificial bee colony (ABC), cuckoo search (CS), teaching–learning-based optimization (TLBO), teaching–learning-based artificial bee colony (TLABC) and a modified version of TLABC proposed in this work, known as MTLABC. This version is a hybridization between TLABC and Levy flight where the search equations of TLABC are changed according to Levy flight equations; this modification, based on the experimental results, yields a significant improvement in TLABC. Various numbers of thresholding levels are tried to compare the performance of the optimization algorithms at multiple dimensions. The performance is measured according to five measures: the objective function, CPU time, peak noise-to-signal ratio, structural similarity index and color feature similarity. These measures indicate that our proposed algorithm, with the best values of the measures in most images and levels, ranks first. Also, Friedman and Wilcoxon signed-rank tests are used to analyze the results statistically. These two tests prove that our proposed algorithm is significantly different from the other four algorithms.