Remote sensing image classification of fuzzy C-means clustering based on the chaos ant colony algorithm

The fuzzy c-means (FCM) clustering algorithm obtains the initial clustering center by random selecting in the research of remote sensing image classification, which makes the FCM algorithm tend to be immersed into the dilemma of local optimal solution, and the FCM clustering algorithm has the difficulty to determine the number of clusters. In order to address these issues, we combine the FCM algorithm with the chaos ant colony algorithm to present an advanced FCM clustering algorithm. The initial clustering center and the number of clustering centers of remote sensing images are obtained as input data for the FCM algorithm with the advantage of ergodicity, global search and robustness in the chaos ant colony algorithm. Evaluating of obtained results from the classification accuracy of images shows the effectiveness of the advanced algorithm.