An improved form of the ant lion optimization algorithm for image clustering problems

Abstract

Thispaperproposesanimprovedformoftheantlionoptimizationalgorithm(IALO)tosolveimageclustering problem. The improvement of the algorithm was made using a new boundary decreasing procedure. Moreover, a recently proposed objective function for image clustering in the literature was also improved to obtain well-separated clusters while minimizing the intracluster distances. In order to accurately demonstrate the performances of the proposed methods, firstly, twenty-three benchmark functions were solved with IALO and the results were compared with the ALO and a chaos-based ALO algorithm from the literature. Secondly, four benchmark images were clustered by IALO and the obtained results were compared with the results of particle swarm optimization, artificial bee colony, genetic, and K- means algorithms. Lastly, IALO, ALO, and the chaos-based ALO algorithm were compared in terms of image clustering by using the proposed objective function for three benchmark images. The comparison was made for the objective function values, the separateness and compactness properties of the clusters and also for two clustering indexes Davies– Bouldin and Xie–Beni. The results showed that the proposed boundary decreasing procedure increased the performance of the IALO algorithm, and also the IALO algorithm with the proposed objective function obtained very competitive results in terms of image clustering.

Ant Lion Optimization: Variants, Hybrids, and Applications

“…Toz in [117] proposed a new version of ALO called IALO by introducing new decreasing boundary instead of stepby-step decreasing for shrinking of the boundary. This new procedure is inspired by decrement of the VOA [118].…”

“…Oliva et al [169] tried to enhance the segmentation image quality by using ALO with Multilevel thresholding (MTH). Toz [117] introduced a new approach to improve clustering quality. They compared their algorithm with particle swarm optimization, artificial bee colony, genetic, and K-means algorithms.…”

User profiling for TV program recommendation based on hybrid television standards using controlled clustering with genetic algorithms and artificial neural networks

“…Toz's work [20] proposed an improved form of the ant lion optimization algorithm to solve image clustering problems using a new boundary-decreasing procedure and to obtain well-separated clusters while minimizing the intracluster distances. The experiments showed an improvement in the algorithm and very competitive image clustering results.…”

A novel approach for nature‐based optimization algorithms: The threat factor approach

“…Several algorithm included in this class are imperialist competitive algorithm, 31 football game algorithm, 32 poor and rich optimization, 33 dynastic optimization algorithm, 34 and teaching-learning-based optimization. 35 The popularity of these algorithms is come from that they are widely used in solving nearly all the engineering problems such as the data and image clustering problems, 28,36,37 antenna arrays synthesis problem, 38 inverse kinematics problem of the robot manipulators, 39 and mechanical design optimization problems. 35 However, according to the no free lunch theorem, there is no optimization algorithm that can find the best solution for every kind of optimization problems.…”

“…The techniques used in these studies can be grouped as changing initial population determination strategies, [41][42][43][44][45] changing randomize number generation strategies, [46][47][48] using different mathematical theories such as chaos, 39,[49][50][51][52][53] hybridization of two or more algorithms, 37,[54][55][56][57][58][59][60] and problem-specific improvements. 36,38,[61][62][63] Although, all these techniques proposed improvements in the related algorithms, generally, they are algorithm-specific techniques.…”