Image denoising by using PDE and GCV in tetrolet transform domain

摘要

The proposed algorithm, which uses partial differential equations (PDE) and generalized cross validation (GCV) theory in the tetrolet transform domain, is used to reduce the noise in an image. Tetrolet transform is applied to decompose the noisy image and GCV theory is used to determine the optimal denoising threshold in the tetrolet transform domain. Then inverse tetrolet transform is used to the modified tetrolet transform coefficients to obtain initial denoising image. PDE model is employed to reduce the block effect which is occurred by only using tetrolet transform to reduce noise, and keeping the edge information. The proposed image denoising algorithm is compared with five similar image denoising algorithms: wavelet transform combined with PDE, contourlet transform combined with PDE, curvelet transform combined PDE, shearlet transform combined with PDE and tetrolet transform combined with PDE, respectively. The experimental results show that comprehensive denoising performance of the proposed algorithm combined with PM1 model (Tetrolet+GCV+PM1) is optimal, especially when PSNR is low. More edges and details can be remained well by the proposed algorithm.