Genetic algorithm based on anisotropic diffusion for super-resolution image restoration

被引：0

作者：

Sun, Yangguang ^{[1
]}

Cai, Chao ^{[1
]}

Zhou, Chengping ^{[1
]}

Ding, Mingyue ^{[1
,2
]}

Zhang, Songgen ^{[3
]}

机构：

[1] Huazhong Univ Sci & Technol, Inst Pattern Recognit Artificial Intelligence, Image Proc & Intelligent Control Key Lab Educ Min, Wuhan 430074, Peoples R China

[2] Huazhong Univ Sci & Technol, Coll Life Sci & Technol, Wuhan 430074, Peoples R China

[3] Beijing Tsinghua R&D Ind Inst, Beijing 10085, Peoples R China

来源：

REMOTE SENSING AND GIS DATA PROCESSING AND APPLICATIONS; AND INNOVATIVE MULTISPECTRAL TECHNOLOGY AND APPLICATIONS, PTS 1 AND 2 | 2007年 / 6790卷

基金：

中国国家自然科学基金;

关键词：

genetic algorithm; anisotropic diffusion; super-resolution; image restoration;

D O I：

10.1117/12.750455

中图分类号：

TP7 [遥感技术];

学科分类号：

081102 ; 0816 ; 081602 ; 083002 ; 1404 ;

摘要：

The blind image restoration based on the nonlinear inverse heat diffusion equation and total variation model has been developed in the past decades. In this paper, a novel genetic algorithm by combining genetic algorithm with anisotropic diffusion technique is put forward to implement the super-resolution image restoration. In the procedure of mutation, we proposed a new genetic mutation operator based on anisotropic diffusion to guide the mutation. The solution space with the higher resolution is formed by the introduction of the new genetic mutation operator. The validity and robustness of our method was demonstrated by using aerial images.

引用

页数：7