Validation of classical and blind criteria for image quality evaluation

Authors:
Michal Haindl;Stanislava Šimberová
Affiliations:
Institute of Information Theory and Automation, Academy of Sciences, Prague, Czech Republic;Astronomical Institute, Academy of Sciences, Ondrejov, Czech Republic
Venue:
SIP '07 Proceedings of the Ninth IASTED International Conference on Signal and Image Processing
Year:
2007

Citing 3
Cited 0

Enhanced performance metrics for blind image restoration

ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part I
Unsupervised image restoration and edge location using compound Gauss-Markov random fields and the MDL principle

IEEE Transactions on Image Processing
Bayesian multichannel image restoration using compound Gauss-Markov random fields

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

An information of image quality and / or performance of image restoration methods can be expressed by evaluative criteria. The classical criteria are used for rather unrealistic image evaluation while the original (undegraded) image is available. More difficult case is in image restoration assessment when the original is unknown. Blind criteria serve as an image quality estimator based on the restored image. Criteria are tested and compared on the synthetic degraded data set (the "ideal" is known) to set out the most appropriate criterium for the real astronomical images. Results are discussed from various points of view of image degradation process including iffluence of the variable noise.