SAR image matching based on SIFT keypoints and multi-subregions information

Conventional image matching methods hardly consider the location relationships between matching points, reducing the reliability and accuracy of matching results. A novel matching mode based on SIFT (scale-invariant feature transform) keypoints and multi-subregions information is proposed in this paper. The new strategy breaks the isolation between matching points, also inhibits the deficiency caused by differences in gray for SAR (synthetic aperture radar) images. The experimental results show that the proposed algorithm is effective and robust.