Matching of SAR images and optical images based on edge feature extracted via SVM

A novel algorithm for matching synthetic aperture radar (SAR) image to optical image based on edge feature using Hausdorff distance combined with genetic algorithm is proposed in this paper. A new method is presented to extract edge feature from low signal to noise ratio SAR image via support vector machine (SVM). Based on, the least squares support vector machine (LS-SVM), a set of the new gradient operators and the corresponding second derivative operators are obtained. Modified Hausdorff distance is adopted as a similarity measure and genetic algorithm is used as searching strategy. Experimental results demonstrate that the algorithm is feasible, fast and can achieve high matching accuracy.