Segmentation Parameter Estimation Algorithm Based on Curvelet Transform Coefficients Energy for Feature Extraction and Texture Description of SAR Images

Synthetic aperture radar (SAR) images have very applications in the field of target recognition, mineral detection, weather forecasting, agricultural, etc. due to their high spatial resolution and imaging technology. However, the process of this type of images is difficult because of the existence of speckle noise. Nowadays, texture region segmentation based on designing a Kernel function with proper parameters is a real challenge. In this paper, a new parameter estimation algorithm has been proposed to design an efficient Kernel function for texture segmentation of SAR images. In this method, the Curvelet transform is applied to the SAR image only in one step and the inner layer coefficients as texture features are extracted. Then, a new Kernel function is formed based on the kurtosis value of the Curvelet coefficients energy (KCE). In the next step, the segmentation of different textures is applied by using the estimated KCE Kernel function. Experimental results on both simulated and real SAR images demonstrate that the proposed algorithm is effective for segmentation and description of different textures in SAR images, and it has also the less segmentation error in comparison with other methods.