An efficient approach for removal of universal noise using Adaptive Based Switching Bilateral Filter

This paper, deals with an Adaptive based Switching Bilateral Filter for removing universal noise in highly corrupted image. In contrast with the previous approach where blurring occurs while filtering the entire image without considering the uncorrupted pixels, which is reduced here by using Adaptive Median Filter with binary vector (BV). Operation carries in three stages. At first an Adaptive Median Filter is used to identify the corrupted pixels to remove the mixed impulses. At the second stage, the edge is preserved by using edge detector and the noise detector is to classify the noisy pixels, whether it is impulse noise or Gaussian noise. The noise detector has a high noise detection rate and high classification rate. In the third stage, the Switching Bilateral Filter (SBF) with sorted quadrant median vector (SQMV) scheme for removing universal noise and also restores the output image. The proposed Adaptive based Switching Bilateral Filter achieves high peak signal-to-noise ratio and great image quality by effectively removing universal noise.