Abstract
Restoration of an image distorted by a system of random impulse response is studied in the presence of additive measurement noise. Iterative methods that are based on modifications of the Wiener and the minimum-variance-unbiased (MVU) estimation methodologies are investigated. These estimators are nonlinear. Using an example of an image distorted by diffraction-limited blur accompanied by impulse-response noise as well as measurement noise, it is found that the iterative MVU estimator outperforms other estimators.
© 1985 Optical Society of America
Full Article | PDF ArticleMore Like This
Rabab K. Ward and Bahaa E. A. Saleh
J. Opt. Soc. Am. A 3(6) 800-807 (1986)
Bahaa E. A. Saleh and Madjid Rabbani
J. Opt. Soc. Am. 73(1) 66-70 (1983)
Xiaotian Shi and Rabab K. Ward
J. Opt. Soc. Am. A 9(3) 364-370 (1992)