Robustness of a mathematical symbiotic system on segmenting SAR imagery

The reported work describes an experiment that evaluates the performance of a hybrid segmentation algorithm on speckled imagery. The particular hybrid algorithm considered was developed using a technique called mathematical symbiosis. The results show that the algorithm is able to correctly extract whole region shapes from the test images, even if the region shapes were almost adjoining each other. The results also show that the algorithm yields misclassification error rates that are below four percent for most of the test images.<
>