An novel image segmentation framework by cooperative learning and evolutionary two-objective kernel clustering

This paper aims to present two novel techniques in synthetic aperture radar (SAR) image segmentation by cooperative competition, cooperative learning and evolutionary multi-objective clustering in kernel mapping thereof. First, we introduce an efficient implementation of cooperative/competition evolution by using two parallel implemented populations, which are divided by the Pareto domination and local density information. Second, two conflicting fuzzy clustering validity indices are incorporated into this framework and optimized in kernel distance measure simultaneously and. Finally, the proposed algorithm is tested on two complicated SAR images. Compared with four other state-of-the-art algorithms and our method achieve comparable results in terms of convergence, diversity metrics, and computational time.