Journal Article

New comparative approach to multi-level thresholding: chaotically initialized adaptive meta-heuristic optimization methods

Kaya, Turgay, Serbet, Fatmanur

2025

Overview

One method aimed at enhancing the performance of meta-heuristic optimization techniques is the incorporation of chaotic systems. Instead of irregular distributions in the search space, chaotic distributions are employed in the initial population of optimization algorithms to improve the efficiency of the search process. This approach enables search agents distributed in a chaotic manner to effectively explore the search space. The initial populations of both the well-established PSO algorithm and the enhanced WSO algorithm, which incorporates advanced search techniques, are distributed in the search space according to the characteristics of Logistic, Chebyshev, Circle, Sine, and Piecewise chaotic maps in this study. The original PSO and WSO algorithms, as well as the resulting chaotically initialized PSO and chaotically initialized WSO algorithms, were tested using 23 benchmark functions. Subsequently, the Otsu method was integrated into the tested optimization algorithms to obtain multi-level thresholding values. These algorithms were applied to five different test images with a manually determined number of thresholds. The results obtained were presented in the study and evaluated using statistical tests.

• Publisher: Springer London,Springer Nature B.V
• Subject: Algorithms / Artificial Intelligence / Chebyshev approximation / Computational Biology/Bioinformatics / Computational Science and Engineering / Computer Science / Data Mining and Knowledge Discovery / Heuristic / Heuristic methods / Image Processing and Computer Vision / Optimization / Optimization algorithms / Optimization techniques / Original Article / Probability and Statistics in Computer Science / Search process / Statistical tests