An improved image non-blind image deblurring method based on FoEs

Qidan Zhu; Lei Sun

doi:10.1117/12.2013421

13 March 2013 An improved image non-blind image deblurring method based on FoEs

Qidan Zhu, Lei Sun

Proceedings Volume 8783, Fifth International Conference on Machine Vision (ICMV 2012): Computer Vision, Image Analysis and Processing; 87830G (2013) https://doi.org/10.1117/12.2013421
Event: Fifth International Conference on Machine Vision (ICMV 12), 2012, Wuhan, China

Abstract

Traditional non-blind image deblurring algorithms always use maximum a posterior(MAP). MAP estimates involving natural image priors can reduce the ripples effectively in contrast to maximum likelihood(ML). However, they have been found lacking in terms of restoration performance. Based on this issue, we utilize MAP with KL penalty to replace traditional MAP. We develop an image reconstruction algorithm that minimizes the KL divergence between the reference distribution and the prior distribution. The approximate KL penalty can restrain over-smooth caused by MAP. We use three groups of images and Harris corner detection to prove our method. The experimental results show that our algorithm of non-blind image restoration can effectively reduce the ringing effect and exhibit the state-of-the-art deblurring results.

Citation Download Citation

Qidan Zhu and Lei Sun "An improved image non-blind image deblurring method based on FoEs", Proc. SPIE 8783, Fifth International Conference on Machine Vision (ICMV 2012): Computer Vision, Image Analysis and Processing, 87830G (13 March 2013); https://doi.org/10.1117/12.2013421

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