Unsupervised classification of satellite imagery: choosing a good algorithm

In the context of land-cover classification with multispectral satellite data several unsupervised classification (clustering) algorithms are investigated and compared with regard to their ability to reproduce ground data in a complex landscape. Ground data is extended to the entire scene using a supervised neural network classification algorithm. The clustering algorithms examined are K-means, extended K-means, agglomerative hierarchical, fuzzy K-means and fuzzy maximum likelihood. Fuzzy clustering is found to perform best relative to a reference scene obtained with the Landsat Thematic Mapper 5 (TM5) platform.