A statistical active contour model for SAR image segmentation

A statistical active contour model is developed for segmenting synthetic ap erture radar (SAR) images into regions of homogeneous speckle statistics. T he technique measures both the local tone and texture along the contour so that no smoothing across segment boundaries occurs. A smooth contour is fav oured by the inclusion of a curvature constraint, whose weight is determine d analytically by considering the model energy balance. The algorithm spawn s smaller snakes to represent multiply connected regions. The algorithm is capable of segmenting noisy SAR imagery whilst accurately depicting (to wit hin 1 pixel) segment boundaries. (C) 1999 Elsevier Science B.V. All rights reserved.