Quality evaluation of the estimation of PSF for license plate image

Kefeng Deng

doi:10.1117/12.632720

24 June 2005 Quality evaluation of the estimation of PSF for license plate image

Kefeng Deng

Proceedings Volume 5960, Visual Communications and Image Processing 2005; 59604G (2005) https://doi.org/10.1117/12.632720
Event: Visual Communications and Image Processing 2005, 2005, Beijing, China

Abstract

License plate recognition (LPR) has been widely deployed in many practical applications. In some situations, the license plate images we acquired are degraded due to the imperfect of image capturing process. Before they are input into the license plate recognition system for recognition, it is first needed to restore them. Many existing methods endeavor to estimate the parameters of the PSF. Yet, they can only give a rough estimation. In practice, in order to get a satisfactory restored image, it is usually needed to evaluate the quality of the estimation of the PSF and tune the parameters. This paper presents such a parameter tuning method for the restoration of license plate image. The parameters of the PSF estimated by our previous method are used as the initial values, and the quality of the restored image is evaluated using a novel image quality assessment measure. The parameters of the PSF are then tuned around the initial parameters according to evaluation result. Experiments show that this approach can achieve restored license plate images with high quality. The quality assessment method may also be extended to more general context.

Citation Download Citation

Kefeng Deng "Quality evaluation of the estimation of PSF for license plate image", Proc. SPIE 5960, Visual Communications and Image Processing 2005, 59604G (24 June 2005); https://doi.org/10.1117/12.632720

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