A new super-resolution image reconstruction method based on hybrid genetic algorithm

Author

Mei, Liu ; WeiDong, Liu ; DeQing, Sun ; Guoqiao, Chen ; Huinian, Liu

Author_Institution

Dept. of Electron. & Commun. Eng., Harbin Inst. of Technol., China

Volume

1

fYear

2004

fDate

2-4 Sept. 2004

Firstpage

211

Abstract

A new super-resolution image reconstruction method is presented, which is based on the hybrid genetic algorithm embedded with gradient descent. It provides a higher quality reconstruction image and improves resolution by 4 times from 9 low-resolution frames. This method reconstructs a high-resolution image through an optimal estimation of the original image. It differs from those methods based on the iterative solution of equation and can improve the quality of CCD image greatly. It can also improve the convergence rate of the simple genetic algorithm.

Keywords

convergence of numerical methods; estimation theory; genetic algorithms; gradient methods; image reconstruction; image resolution; CCD image quality; convergence rate; gradient descent method; hybrid genetic algorithm; image resolution; iterative methods; optimal image estimation; super resolution image reconstruction method; Cameras; Charge coupled devices; Equations; Genetic algorithms; Image reconstruction; Image resolution; Iterative algorithms; Iterative methods; Layout; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications, 2004. Proceedings of the 2004 IEEE International Conference on

Print_ISBN

0-7803-8633-7

Type

conf

DOI

10.1109/CCA.2004.1387213

Filename

1387213