Paper Info
Title
A general framework for kernel similarity-based image denoising
Abstract
Any image can be represented as a function defined on a discrete weighted graph whose vertices are image pixels. Each pixel can be linked to other pixels via graph edges with corresponding weights derived from similarities between image pixels (graph vertices) measured in some appropriate fashion. Image structure is encoded in the Laplacian matrix derived from these similarity weights. Taking advantage of this graph-based point of view, we present a general regularization framework for image denoising. A number of well-known existing denoising methods like bilateral, NLM, and LARK, can be described within this formulation. Moreover, we present an analysis for the filtering behavior of the proposed method based on the spectral properties of Laplacian matrices. Some of the well established iterative approaches for improving kernel-based denoising like diffusion and boosting iterations are special cases of our general framework. The proposed approach provides a better understanding of enhancement mechanisms in self similarity-based methods, which can be used for their further improvement. Experimental results verify the effectiveness of this approach for the task of image denoising.
Year
DOI
Venue
2013
10.1109/GlobalSIP.2013.6736903
Global Conference Signal and Information Processing
Keywords
DocType
ISSN
filtering theory,graph theory,image denoising,image enhancement,image representation,iterative methods,matrix algebra,spectral analysis,LARK method,Laplacian matrix,NLM method,bilateral method,boosting iteration,denoising methods,diffusion iteration,discrete weighted graph,enhancement mechanisms,filtering behavior,general regularization framework,graph edges,graph vertices,image pixels,image representation,image structure,iterative approaches,kernel similarity-based image denoising,kernel-based denoising,self similarity-based methods,similarity weights,spectral property,Graph Laplacian,Image Denoising,Kernel Similarity Matrix
Conference
2376-4066
Citations 
PageRank 
References 
15
0.68
12
Authors
2
Name
Order
Citations
PageRank
Amin Kheradmand1583.84
Peyman Milanfar23284155.61