Segmentation of radar images by combining watershed and Fisher techniques for target classification

In the area of monitoring and observation by sea, land or air by the use of information is an important task for the decision. We are interested in the present work on the information processing for the recognition of radar targets from ISAR images. To provide the information necessary for the recognition phase, we propose an approach radar image processing based on the combination algorithms Fisher and watershed. This combination allows us to obtain closed shapes (edge). Then, we proceed to a shape modeling based on the Fourier descriptor. Finally, we use the KNN classifier to evaluate the performance of our approach. The obtained results seem good.