SAR image matching using an improved SIFT-based anisotropic diffusion algorithm
Pratham Gupta, Preeti Modi, Sourabh Paul, Saurav Gupta · Journal of Spatial Science · 2024
In this paper, we propose a new image matching algorithm for the synthetic aperture radar (SAR) images with significant local as well global geometric differences. The noise handling capability of descriptor and an appropriate feature-matching technique are the crucial factors in SAR image matching as these images are highly influenced by speckle noise. To address these issues, an effective SAR image matching scheme is proposed using an improved scale-invariant feature transform (SIFT)-based anisotropic diffusion. This algorithm constructs SIFT scale layers based on anisotropic diffusion which removes the influence of speckle noise. Then, a local feature-matching algorithm is proposed to take care of the local deformations between SAR images. Experiments on multiple sets of SAR images indicate that the proposed method is competent to provide better matching performance.