Radar image segmentation using active contour

A new method for texture image segmentation is proposed which has three advantageous. Firstly, it has excellent texture discrimination and low complexity, for uniform LBP/C (local binary patterns and pattern contrasts) operator which reduces the number of texture pattern to 23% is used to extract texture features from a texture image. Secondly, active contours without edges are improved so that the LBP/C histogram can be used to evolve the initial curve during the segmentation process. A multiple object texture image can be segmented, because the proposed model is expanded to multiphase segmentation by the hierarchical method which can avoid the problem due to the choice of initial conditions. Finally, the speed of image segmentation is higher, for AOS scheme is applied for the numerical solution of the proposed method. Experiments on both synthetic and remote sensing images show that the proposed method is more accurate and faster.