Image denoising study on Nonlocal-Means Filter

Author

Deng Shi-wo ; Jin Ling-yu ; Xu Xiong-qiang ; Ma Wei-bin

Author_Institution

Dept. of Math., South China Agric. Univ., Guangzhou, China

fYear

2012

fDate

9-11 Nov. 2012

Firstpage

1

Lastpage

4

Abstract

In this paper, we present a new model-Nonlocal PM Model after combining the Nonlocal Means (NLM) filter and the PM-equation model. The decay parameter h acts as a filtering parameter and the standard deviation a of Gaussian kernel G_a(·); both are very important parameters in the Nonlocal Means Filter, and the gradient modulus threshold k that controls the conduction are obtained by setting the maximum of the peak signal-to-noise ratio (PSNR in db) as the goal in the numerical experiment of the Nonlocal PM Model. The experimental results show the new method has better performance in image denoising.

Keywords

Gaussian noise; filtering theory; gradient methods; image denoising; statistical analysis; Gaussian kernel; PM equation model; PSNR; decay parameter; filtering parameter; gradient modulus threshold; image denoising; nonlocal PM model; nonlocal-means filter; peak signal-to-noise ratio; standard deviation; Equations; Mathematical model; Numerical models; PSNR; Wiener filters; Gaussian noise distribution; Nonlocal Means Filter; Nonlocal PM model; P-M equation;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Signal Processing (IASP), 2012 International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-1-4673-2547-9

Type

conf

DOI

10.1109/IASP.2012.6424997

Filename

6424997