Skip to Main Content
Due to its inherent complexity, remote sensing image clustering is a challenging task. Recently, some spatial-based clustering approaches have been proposed; however, one crucial factor with regard to their clustering quality is that there is usually one parameter that controls their spatial information weight, which is difficult to determine. Meanwhile, the traditional optimization methods of the objective functions for these clustering approaches often cannot function well because they cannot simultaneously possess both a local search capability and a global search capability. Furthermore, these methods only use a single optimization method rather than hybridizing and combining the existing algorithmic structures. In this paper, an adaptive fuzzy clustering algorithm with spatial information for remote sensing imagery (AFCM_S1) is proposed, which defines a new objective function with an adaptive spatial information weight by using the concept of entropy. In order to further enhance the capability of the optimization, an adaptive memetic fuzzy clustering algorithm with spatial information for remote sensing imagery (AMASFC) is also proposed. In AMASFC, the clustering problem is transformed into an optimization problem. A memetic algorithm is then utilized to optimize the proposed objective function, combining the global search ability of a differential evolution algorithm with a local search method using Gaussian local search (GLS). The optimal value of the specific parameter in GLS, which determines the local search efficiency, can be obtained by comparing the objective function increment for different values of the parameter. The experimental results using three remote sensing images show that the two proposed algorithms are effective when compared with the traditional clustering algorithms.