An adaptive multilevel thresholding method with chaotically-enhanced Rao algorithm

• Published in: Multimedia tools and applications Vol. 82; no. 8; pp. 12351 - 12377
• Main Authors: Olmez, Yagmur, Sengur, Abdulkadir, Koca, Gonca Ozmen, Rao, Ravipudi Venkata
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-03-2023; Springer Nature B.V
• Subjects: Algorithms; Chebyshev approximation; Computer Communication Networks; Computer Science; Convergence; Data Structures and Information Theory; Heuristic methods; Image enhancement; Image segmentation; Metaphor; Multilevel; Multimedia Information Systems; Optimization; Optimization techniques; Special Purpose and Application-Based Systems; Statistical analysis; Thresholds; Multilevel thresholding; Image segmentation; Chaotic search; Metaheuristic methods; Rao algorithm
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-022-13671-9

Multilevel image thresholding is a well-known technique for image segmentation. Recently, various metaheuristic methods have been proposed for the determination of the thresholds for multilevel image segmentation. These methods are mainly based on metaphors and they have high complexity and their convergences are comparably slow. In this paper, a multilevel image thresholding approach is proposed that simplifies the thresholding problem by using a simple optimization technique instead of metaphor-based algorithms. More specifically, in this paper, Chaotic enhanced Rao (CER) algorithms are developed where eight chaotic maps namely Logistic, Sine, Sinusoidal, Gauss, Circle, Chebyshev, Singer, and Tent are used. Besides, in the developed CER algorithm, the number of thresholds is determined automatically, instead of manual determination. The performances of the developed CER algorithms are evaluated based on different statistical analysis metrics namely BDE, PRI, VOI, GCE, SSIM, FSIM, RMSE, PSNR, NK, AD, SC, MD, and NAE. The experimental works and the related evaluations are carried out on the BSDS300 dataset. The obtained experimental results demonstrate that the proposed CER algorithm outperforms the compared methods based on PRI, SSIM, FSIM, PSNR, RMSE, AD, and NAE metrics. In addition, the proposed method provides better convergence regarding speed and accuracy.