The curvelet transform for image denoising：（曲波变换的图像去噪）.pdfVIP

670 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 11, NO. 6, JUNE 2002 The Curvelet Transform for Image Denoising Jean-Luc Starck, Emmanuel J. Candès, and David L. Donoho Abstract—We describe approximate digital implementations of range of wavelet-based tools and ideas have been proposed two new mathematical transforms, namely, the ridgelet transform and studied. Initial efforts included very simple ideas like [2] and the curvelet transform [6], [5]. Our implementations thresholding of the orthogonal wavelet coefficients of the noisy offer exact reconstruction, stability against perturbations, ease of implementation, and low computational complexity. A central data, followed by reconstruction. Later efforts found that sub- tool is Fourier-domain computation of an approximate digital stantial improvements in perceptual quality could be obtained Radon transform. We introduce a very simple interpolation in by translation invariant methods based on thresholding of an Fourier space which takes Cartesian samples and yields samples undecimated wavelet transform. More recently, “tree-based” on a rectopolar grid, which is a pseudo-polar sampling set based wavelet denoising methods were developed in the context of on a concentric squares geometry. Despite the crudeness of our interpolation, the visual performance is surprisingly good. Our image denoising, which exploit the tree structure of wavelet ridgelet transform applies to the Radon transform a special coefficients and the so-called parent–child correlations which overcomplete wavelet pyramid whose wavelets have compact