Alternate PSO-Based Adaptive Interval Type-2 Intuitionistic Fuzzy C-Means Clustering Algorithm for Color Image Segmentation

• Published in: IEEE access Vol. 7; pp. 64028 - 64039
• Main Authors: Zhao, Feng, Chen, Yilei, Liu, Hanqiang, Fan, Jiulun
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; alternate optimization; Clustering; Clustering algorithms; Color; Color imagery; Fuzzy sets; Image segmentation; interval type-2 fuzzy clustering; intuitionistic fuzzy set; Land use; Linear programming; Optimization; Particle swarm optimization; Uncertainty
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2916894

Interval type-2 fuzzy c-means (IT2FCM) clustering algorithm can describe more uncertainty than fuzzy c-means (FCM) clustering algorithm by using two fuzzifiers to construct a more inclusive boundary. How to obtain appropriate fuzzifiers and initialize cluster centers are essential tasks for the IT2FCM. To effectively solve these problems, this paper proposes an alternate particle swarm optimization-based adaptive interval type-2 intuitionistic fuzzy c-means clustering algorithm (A-PSO-IT2IFCM) and applies this proposed method to color image segmentation. First, in order to further deal with the uncertainty, a novel interval type-2 fuzzy clustering objective function is constructed by utilizing the intuitionistic fuzzy information extracted from images. Then an alternate particle swarm optimization (PSO) scheme is designed to optimize fuzzifiers and cluster centers alternatively. In addition, a multiscale update strategy for the positions of particles is introduced into the A-PSO-IT2IFCM to increase the diversity of swarm and boost the convergence of optimization. The color image segmentation experiments on Berkeley and UC Merced Land Use datasets show that the proposed algorithm can adaptively determine fuzzifiers and cluster centers and achieve good segmentation results.