Adaptive mixed image denoising based on image decomposition

Abstract

Abstract. Image denoising while preserving image features is a key problem in image processing and computer vision. This letter proposes an adaptive mixed method for image restoration. First, this method decomposes a given image as the sum of two components: geometric structure and oscillating pattern according to Meyer's theory. Second, a coupled bidirectional diffusion equation is used to restore the structure part, and a nonlocal means filter is used to remove noise in the oscillating part. Experimental results show advantages of this method in feature-preserving denoising. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).

Patch-based and multiresolution optimum bilateral filters for denoising images corrupted by Gaussian noise

“…Yang et al extended the work by Durand et al and proposed an O (1) algorithm for arbitrary range and arbitrary spatial kernels. Liu et al 25 proposed to decompose an image as the sum of geometric structure and oscillating pattern. The RC kernel approximates the Gaussian range kernel more accurately for the same number of terms than the polynomial approximation.…”

A Simple Fuzzy Method to Remove Mixed Gaussian-Impulsive Noise From Color Images

“…In this context, recently, it has been proposed to use different minimization terms to reduce the different noise types [25], to employ segmentation followed by regularization [26], and to combine statistical noise detection and regularization [27]. Other approaches propose to employ image decomposition to separate and reduce noise [28], robust gradient vector flow and diffusion models [29], or finite element techniques [30]. Also, the problem of mixed PoissonGaussian noise removal is studied in [31].…”