Title :
On Choosing Wavelet Resolution in Image Deblurring
Author :
Cavalier, Laurent ; Raimondo, Marc
Author_Institution :
Univ. of Aix-Marseille, Marseille
Abstract :
In wavelet deblurring of noisy images the finest resolution levels are key parameters which require fine tuning. In this paper we present a blockwise thresholding rule in the Fourier domain to derive near-optimal finest re solution levels for a large class of blurred-image scenarios. Numerical results based on the WaveD fast algorithm illustrate the improvement over the current WaveD setting
Keywords :
Fourier transforms; image resolution; image restoration; wavelet transforms; Fourier domain; WaveD fast algorithm; blockwise thresholding rule; image deblurring; near-optimal finest resolution level; wavelet resolution; Adaptive algorithm; Additive noise; Deconvolution; Electronics packaging; Fast Fourier transforms; Image resolution; Image restoration; Kernel; Noise level; Wavelet domain;
Conference_Titel :
Computer Graphics, Imaging and Visualisation, 2006 International Conference on
Conference_Location :
Sydney, Qld.
Print_ISBN :
0-7695-2606-3
DOI :
10.1109/CGIV.2006.68
