Skip to Main Content
Interpretation of aerial images is an important task in various military and non-military applications. Image segmentation can be viewed as the essential step of extracting features in aerial images. Among many developed segmentation methods, the clustering methods have been extensively investigated and used. The determination of the number of clusters in a dataset is inherently a difficult problem, especially when the a priori information on the dataset is unavailable. In this paper, we propose a genetic algorithm-based clustering approach for aerial image segmentation. Our approach has two advantages: it can automatically determine the proper number of clusters and cluster the data according to the cluster validity index. The performance of the proposed approach is evaluated in conjunction with two cluster validity indices, namely Davies-Bouldin index and Xie-Beni index, respectively. Experimental results are provided to illustrate the feasibility of the proposed approach.