Image Denoising with BEMD and Edge-Preserving Self-Snake Model

Image denoising is important in digital image processing. In this paper, an image denoising method using edge-preserving self-snake model(ESM) and bidimensional empirical mode decomposition(BEMD) is presented. The ESM includes an edge stopping function which is constructed with nonlocal gradient having maximum peak only at edges and good tolerance for noise. This model can preserve edge information while removing noise from digital images. The BEMD transforms the image into intrinsic mode functions(IMFs) and residue. Different components of IMFs present different frequency of the image. we use ESM of the IMFs to filter noise. Finally, we reconstruct the image with the filtered IMFs and residue. Experiments show that this algorithm has a better result than ESM.