Fuzzy C-means and principal component analysis based GPR image enhancement

In this paper, a ground penetrating radar image enhancement scheme based on fuzzy c-means and principal component analysis is proposed. The original image is decomposed into clutter, noise and target subspaces using principal component analysis. Fuzzy c-means is used to assign weights to different subspaces based on their membership values. Simulation results demonstrate that the proposed scheme can detect (single and multiple) targets, provide better mean square error and peak signal to noise ratio.