A local feature with rotation-invariance based on gradient ratio for SAR image
Qing Wang, Tao Tang, Yi Su · 2016
LBP operator shows good performance on rotation invariant while LGRPH is robust to multiplicative noise and gradient changes. In order to combine merits of both operators, an improved rotation invariant feature for SAR image is proposed in this paper. Experiments on SAR images demonstrate that the proposed feature has a good performance on targets recognition and image texture patches matching with various orientation angles.