Adaptive Gaussian Noise Image Removal Algorithm Using Filtering-Based Noise Estimation  

作　　者：Tuan-anh NGUYEN Hong-son NGUYEN Min-cheol HONG 

机构地区：[1]Dept.of Information and Telecommunication,Soongsil University

出　　处：《Journal of Measurement Science and Instrumentation》2011年第3期230-234,共5页测试科学与仪器（英文版）

基　　金：supported by the Korea Science and Engineering Foundation(KOSEF) grant fund by the Korea Govern-ment(MEST)(No.2011-0000148);the Ministry of Knowledge Economy,Korea under the Infor mation Technology Research Center support programsupervised by the National IT Industry Promotion Agency(NIPA-2011-C1090-1121-0010)

摘　　要：This paper proposes a spatially denoising algorithm using filtering-based noise estimation for an image corrupted by Gaussian noise.The proposed algorithm consists of two stages:estimation and elimination of noise density.To adaptively deal with variety of the noise amount,a noisy input image is firstly filtered by a lowpass filter.Standard deviation of the noise is computed from different images between the noisy input and its filtered image.In addition,a modified Gaussian noise removal filter based on the local statistics such as local weighted mean,local weighted activity and local maximum is used to control the degree of noise suppression.Experiments show the effectiveness of the proposed algorithm.

关 键 词：DENOISING local statistics Gaussian filtering noise estimation Gaussian noise 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]