南京理工大学学报（自然科学版）2016，Vol.40Issue(4)：404-409,6.DOI:10.14177/j.cnki.32-1397n.2016.40.04.005
泊松噪声污染模糊图像的非盲去卷积方法
Non-blind deconvolution method for blurred image contaminated by Poisson noise
董文德 1杨新民 1段然 1郭晓鸿 1林丹 1秦树鑫1
作者信息
- 1. 中国电子科技集团公司 第二十八研究所，江苏 南京210007
- 折叠
摘要
Abstract
This paper proposes a non-blind image deconvolution method for restoring blurred image contaminated by Poisson noise. This method is constructed based on the Poisson noise model and in-troduces the Gaussian Scale Mixture Fields of Experts( GSM FoE) for regularization. The problem is solved with the alternating direction method of multipliers( ADMM) . Experimental results show that the proposed method can effectively restore blurred image contaminated by Poisson noise and achieve results of high quality.关键词
泊松噪声/非盲去卷积/高斯尺度混合型马尔科夫专家场/正则化Key words
Poisson noise/non-blind deconvolution/Gaussian scale mixture fields of experts/regular-ization分类
信息技术与安全科学引用本文复制引用
董文德,杨新民,段然,郭晓鸿,林丹,秦树鑫..泊松噪声污染模糊图像的非盲去卷积方法[J].南京理工大学学报（自然科学版）,2016,40(4):404-409,6.
