ABSTRACT

This paper introduces efficient and fast algorithms for unsupervised image segmentation, using low-level features such as color, applied on satellite images. With the increase in spatial resolution of satellite imagery, the image segmentation technique for generating and updating geographical information are becoming more and more important. The present paper describes a satellite image segmentation technique using M-band fuzzy c-Means features. In remotely-sensed multispectral imagery the variations in the reflectivity of surface materials across different spectral bands provide a fundamental mechanism for understanding the image features. Fuzzy methods in remote sensing have received growing interest for their importance in situations where the geographical phenomena are inherently fuzzy. The proposed approach is based on that first enhance multispectral image and then applying clustering technique, using La*b* color space and the vectors are used as inputs for the k-means or fuzzy c-means clustering methods, for a segmented image whose regions are distinct from each other according to color and texture characteristics.