A new cumulant-based active contour model with wavelet energy for segmentation of SAR images

Abstract

In this paper, a new algorithm for segmentation of Synthetic Aperture Radar images using the skewness wavelet energy has been presented. The skewness is the 3rd order cumulant which extracts the statistical properties of each region of a SAR image. SAR images have Nonlinearity in intensity inhomogeneities because of the speckle noise. The algorithm which we proposed in this paper is a region-based active contour model that is able to use the intensity information in local regions. This algorithm also is able to cope with the speckle noise and nonlinear intensity inhomogeneity of SAR images. We use the wavelet energy to analyze each sub-band of a SAR image. The results of the proposed algorithm on the test SAR images of agricultural and urban regions show a good performance of this method.