A New Region-Based Active Contour Model with Skewness Wavelet Energy for Segmentation of SAR Images

Gholamreza AKBARIZADEH  Gholam Ali REZAI-RAD  Shahriar BARADARAN SHOKOUHI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.7   pp.1690-1699
Publication Date: 2010/07/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.1690
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Machine Vision and its Applications)
Category: 
Keyword: 
segmentation,  synthetic aperture radar,  active contours,  level set method,  third order cumulant,  

Full Text: PDF(4.5MB)>>
Buy this Article




Summary: 
A new method of segmentation for Synthetic Aperture Radar (SAR) images using the skewness wavelet energy has been presented. The skewness is the third order cumulant which measures the local texture along the region-based active contour. Nonlinearity in intensity inhomogeneities often occur in SAR images due to the speckle noise. In this paper we propose a region-based active contour model that is able to use the intensity information in local regions and to cope with the speckle noise and nonlinear intensity inhomogeneity of SAR images. We use a wavelet coefficients energy distribution to analyze the SAR image texture in each sub-band. A fitting energy called skewness wavelet energy is defined in terms of a contour and a functional so that, the regions and their interfaces will be modeled by level set functions. A functional relationship has been calculated on these level sets in terms of the third order cumulant, from which an energy minimization is derived. Minimizing the calculated functions derives the optimal segmentation based on the texture definitions. The results of the implemented algorithm on the test images from the Radarsat SAR images of agricultural and urban regions show a desirable performance of the proposed method.