Midfrequency-based real-time blind image restoration via independent component analysis and genetic algorithms

Yihan Luo; Chengyu Fu

doi:10.1117/1.3567072

1 April 2011 Midfrequency-based real-time blind image restoration via independent component analysis and genetic algorithms

Yihan Luo, Chengyu Fu

Author Affiliations +

Optical Engineering, Vol. 50, Issue 4, 047004 (April 2011). https://doi.org/10.1117/1.3567072

Abstract

Blind image restoration (BIR) is a useful tool in image processing but too time-consuming to be applied. In order to truly achieve real-time BIR, an ultrafast method for BIR is proposed based on a new concept called the midfrequency region (MR) of an image, which can be used to estimate the point spread function (PSF) and rapidly and accurately restore the image. Also, new MR-based Wiener filtering is derived to accomplish BIR more quickly. Then, using the PSFs of class G that fit numerous imaging systems, a new MR-based algorithm for real-time BIR is derived via independent component analysis and genetic algorithms. Experiments prove that the algorithm is quite effective, speedy, and stable and can truly accomplish real-time image deblurring in on-line systems.

©(2011) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Yihan Luo and Chengyu Fu "Midfrequency-based real-time blind image restoration via independent component analysis and genetic algorithms," Optical Engineering 50(4), 047004 (1 April 2011). https://doi.org/10.1117/1.3567072

Published: 1 April 2011

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available