A new edge detection method of polarimetric SAR images using the curvelet transform and the Duda operator

A new method for edge detection of polarimetric SAR images is proposed based on the curvelet transform and the Duda operator in this paper. The detection of edge features from SAR images is complicated by the presence of speckle. Firstly, a despeckled polarimetric SAR image is derived by the Polarimetric Whitening Filter (PWF), and then the image is filtered by Lee's method with eight edge-aligned windows to preserve the edge sharpness. The curvelet transform which is a multi-scale representation suited for edge enhancement is applied to estimate the area including edges approximately. Then the Duda operator, a contrast ratio edge detector to extract linear features, is used to give the positions of the edges precisely. The proposed method is applied to PISAR images to illustrate its effectiveness.