Land use classification with textural analysis and the aggregation technique using multi-temporal JERS-1 L-band SAR images

This paper describes a method of improving classification accuracy when usi ng Synthetic Aperture Radar (SAR) images. The classifier used is a maximum likelihood classifier. Texture and textural feature images were made and us ed for classification. The accuracy of various classification methods was c ompared. As a result, it was found that the best classification was produce d by the aggregation of the classified image when using texture images as a dditional inputs to the classifier. It is also shown that textural analysis and the aggregation technique are useful in the classification of SAR imag es.