Maximum 3D Tsallis entropy based multilevel thresholding of brain MR image using attacking Manta Ray foraging optimization. (August 2021)

• Record Type: Journal Article
• Authors: Jena, Bibekananda; Naik, Manoj Kumar; Panda, Rutuparna; Abraham, Ajith
• Is Part Of: Engineering applications of artificial intelligence. Volume 103(2021)
• Publication Date: 2021-08
• Subjects: Machine intelligence -- Soft computing -- Multilevel thresholding -- Brain MRI; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104293
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Nevertheless, the accuracy of a multilevel image thresholding technique using 1D or 2D Tsallis entropy is limited. To overcome this, we propose a maximum 3D Tsallis entropy-based multilevel thresholding method. The idea of 3D Tsallis entropy is introduced. Opposed to the 1D/2D Tsallis entropy, the 3D Tsallis entropy-based approach is more robust, it performs well even in the case of the low signal-to-noise-ratio and contrast. Manta Ray Foraging Optimization (MRFO) algorithm is a newly introduced algorithm to solve the optimization problem by imitating the foraging technique of Manta Ray fish in the ocean using a mathematical model. Due to insufficient energy levels of search agents in MRFO, they fail to avoid local minima and fall on it. To make the algorithm more effective for the segmentation application, we introduce a new algorithm coined as attacking Manta Ray foraging optimization (AMRFO). A set of classical benchmark functions together with composite functions (CEC 2014) is used to validate the proposed AMRFO algorithm. Statistical analysis is implicitly carried out using Wilcoxon's signed-rank test and Friedman's mean rank test. Interestingly, the results show that the proposed AMRFO is superior to the state-of-the-art optimization algorithms. Moreover, the proposed method is also compared with 1D/2D Tsallis entropy-based approaches. To experiment, 100 test images from the AANLIB MR Image dataset are considered. Our method outperforms 1D/2D Tsallis entropy-based approaches. The proposed scheme would be useful for the segmentation of multi-spectral color images. Highlights: A maximum 3D Tsallis entropy-based multilevel thresholding method is fostered. An attacking Manta Ray foraging optimization algorithm is proposed. A new objective function is investigated for maximizing entropy. The quantitative and qualitative analysis using statistical methods is highlighted. Experimental results on brain MR images are presented.