Unsupervised segmentation of the POL-SAR image using similarity parameters in sequential projection pursuit model

A sequential projection pursuit model (SPPM) for unsupervised segmentation of the polarimetric synthetic aperture radar (POL-SAR) image is proposed in this paper. The features of the high dimension data are extracted out via orthogonal projection and the classification is accomplished by the Bayesian decision rule. Also the similarity parameters of POL-data are expressed as the characters of a target and form new target data. The SPPM utilizes new target data to classify the target into various subclasses. Good-segmented results have been obtained for the POL-SAR image processing. The segmented results using the SPPM are better than that of using entropy-alpha plane.