Remote sensing image classification based on dot density function weighted FCM clustering algorithm

Based on the uncertainty and fuzziness of remote sensing images, a dot density function weighted fuzzy C-means (WFCM) clustering algorithm is proposed to carry out the fuzzy classification or the hard classification of remote sensing images. First, the algorithm considering data spatial distribution information and classification fuzziness is described. The fuzzy C-means algorithm is an unsupervised fuzzy classification method. Clustering precision of the algorithm is affected by its equal partition trend for data sets, which leads to the optimal solution of the algorithm may not be the correct partition in the data set of which cluster sample numbers are difference greatly. In order to overcome this drawback, a dot density function WFCM algorithm is proposed in this paper. The method has not only overcome the limitation of FCM to certain extent, but also been favorable convergence. Then the WFCM algorithm would be compared with the K-means algorithms by experiments in LANDSAT TM image. Finally classification result of the algorithms is analyzed systematically, and the experiment result shows the WFCM algorithm can improve classification accuracy for remote sensing images.