Preserving details in restoring images highly corrupted by impulse noiseremains a challenging problem. We proposed an algorithm based on radial basisfunctions (RBF) interpolation which estimates the intensities of corruptedpixels by their neighbors. In this algorithm, first intensity values of noisypixels in the corrupted image are estimated using RBFs. Next, the image issmoothed. The proposed algorithm can effectively remove the highly denseimpulse noise. Experimental results show the superiority of the proposedalgorithm in comparison to the recent similar methods both in noise suppressionand detail preservation. Extensive simulations show better results in measureof peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM),especially when the image is corrupted by very highly dense impulse noise.
展开▼
