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

Liu Mei; Liu WeiDong; Sun DeQuing; Chen Guoqiao; Liu Huinian

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

Liu Mei^*
, Liu WeiDong
, Sun DeQuing
, Chen Guoqiao
, Liu Huinian

^*Corresponding author for this work

School of Electronics and Information Engineering

Sci. and Technol. Devmt. Ctr.
Harbin Institute of Technology

Research output: Contribution to conference › Paper › peer-review

2 Scopus citations

Abstract

A new super-resolution image reconstruction method is presented, which is based on 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 high-resolution image through an optimal estimation of original image. It differs from those methods based on Iterative Solution of Equation and can improve the quality of CCD image greatly. It can also improve the convergence rate of Simple Genetic Algorithm.

Original language	English
Pages	211-216
Number of pages	6
State	Published - 2004
Event	2004 IEEE International Conference on Control Applications - Taipei, Taiwan, Province of China Duration: 2 Sep 2004 → 4 Sep 2004

Conference

Conference	2004 IEEE International Conference on Control Applications
Country/Territory	Taiwan, Province of China
City	Taipei
Period	2/09/04 → 4/09/04

Keywords

Gradient descent
Hybrid genetic algorithm
Image reconstruction
Optimal estimation
Super-resolution

Cite this

@conference{12cd531d40eb446f9f52daa4b7924bcf,

title = "A new super-resolution image reconstruction method based on hybrid genetic algorithm",

abstract = "A new super-resolution image reconstruction method is presented, which is based on 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 high-resolution image through an optimal estimation of original image. It differs from those methods based on Iterative Solution of Equation and can improve the quality of CCD image greatly. It can also improve the convergence rate of Simple Genetic Algorithm.",

keywords = "Gradient descent, Hybrid genetic algorithm, Image reconstruction, Optimal estimation, Super-resolution",

author = "Liu Mei and Liu WeiDong and Sun DeQuing and Chen Guoqiao and Liu Huinian",

year = "2004",

language = "英语",

pages = "211--216",

note = "2004 IEEE International Conference on Control Applications ; Conference date: 02-09-2004 Through 04-09-2004",

}

TY - CONF

T1 - A new super-resolution image reconstruction method based on hybrid genetic algorithm

AU - Mei, Liu

AU - WeiDong, Liu

AU - DeQuing, Sun

AU - Guoqiao, Chen

AU - Huinian, Liu

PY - 2004

Y1 - 2004

N2 - A new super-resolution image reconstruction method is presented, which is based on 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 high-resolution image through an optimal estimation of original image. It differs from those methods based on Iterative Solution of Equation and can improve the quality of CCD image greatly. It can also improve the convergence rate of Simple Genetic Algorithm.

AB - A new super-resolution image reconstruction method is presented, which is based on 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 high-resolution image through an optimal estimation of original image. It differs from those methods based on Iterative Solution of Equation and can improve the quality of CCD image greatly. It can also improve the convergence rate of Simple Genetic Algorithm.

KW - Gradient descent

KW - Hybrid genetic algorithm

KW - Image reconstruction

KW - Optimal estimation

KW - Super-resolution

UR - https://www.scopus.com/pages/publications/17744371715

M3 - 论文

AN - SCOPUS:17744371715

SP - 211

EP - 216

T2 - 2004 IEEE International Conference on Control Applications

Y2 - 2 September 2004 through 4 September 2004

ER -

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

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this