Contourlet-Based Levelset SAR Image Segmentation

Segmentation in Synthetic Aperture Radar (SAR) images has become very important in recent years because of its wide range of applications. There are lots of methods introduced for this purpose in literature. In this paper we used contourlet as a new method for feature extraction. Here the levelset method is used with a statistical based kernel. The parameters of this kernel have been calculated using high order cumulants. For this purpose the estimation of energy distribution in Contourlet transform has been used. Our experimental results show that the proposed method is effective in Image segmentation containing inhomogeneity intensities such as SAR images and also outperforms wavelet based methods.

[1]  Carlos Vázquez,et al.  SAR image segmentation with active contours and level sets , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[2]  Amar Mitiche,et al.  Multiregion level-set partitioning of synthetic aperture radar images , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Zhang Yanning,et al.  SAR Image Segmentation Method Using DP Mixture Models , 2008, 2008 International Symposium on Computer Science and Computational Technology.

[4]  Chunming Li,et al.  Minimization of Region-Scalable Fitting Energy for Image Segmentation , 2008, IEEE Transactions on Image Processing.

[5]  Fang Liu,et al.  Spectral Clustering Ensemble Applied to SAR Image Segmentation , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Olivier Germain,et al.  Edge location in SAR images: performance of the likelihood ratio filter and accuracy improvement with an active contour approach , 2001, IEEE Trans. Image Process..

[7]  Gholamreza Akbarizadeh,et al.  A New Statistical-Based Kurtosis Wavelet Energy Feature for Texture Recognition of SAR Images , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[9]  Zhao Yifan,et al.  Contourlet-Based Feature Extraction on Texture Images , 2008, 2008 International Conference on Computer Science and Software Engineering.

[10]  Philippe Marthon,et al.  An optimal multiedge detector for SAR image segmentation , 1998, IEEE Trans. Geosci. Remote. Sens..