Title :
An Empirical Identification Method of Gaussian Blur Parameter for Image Deblurring
Author :
Chen, Fen ; Ma, Jianglin
Author_Institution :
Coll. of Autom., Univ. of Electron. Sci. & Technol. of China, Chengdu
fDate :
7/1/2009 12:00:00 AM
Abstract :
In this paper, we propose an empirical identification method of the Gaussian blur parameter for image deblurring. The parameter estimate is chosen from a collection of candidate parameters. The blurred image is restored by these candidate parameters under the assumption that the candidate is equal to the true value. The estimate is selected to be at the maximum point of the differential coefficients of restored image Laplacian L1 norm curve. Experimental results are presented to demonstrate the performance of the proposed method.
Keywords :
Gaussian processes; image restoration; parameter estimation; Gaussian blur parameter; Laplacian norm curve; empirical identification method; image deblurring; image restoration; Boundary conditions; Gaussian blur; image deblurring; parameter identification; point spread function (PSF);
Journal_Title :
Signal Processing, IEEE Transactions on
DOI :
10.1109/TSP.2009.2018358