DocumentCode
2885544
Title
Suboptimality of nonlocal means on images with sharp edges
Author
Maleki, Arian ; Narayan, Manjari ; Baraniuk, Richard
Author_Institution
Dept. of Electr. & Comput. Eng., Rice Univ., Houston, TX, USA
fYear
2011
fDate
28-30 Sept. 2011
Firstpage
299
Lastpage
305
Abstract
We conduct an asymptotic risk analysis of the non-local means image denoising algorithm for Horizon class images that are piecewise constant with a sharp edge discontinuity. We prove that the mean-square risk of nonlocal means is suboptimal and in fact is within a log factor of the mean square risk of wavelet thresholding.
Keywords
image denoising; image segmentation; risk analysis; Horizon class imaging; asymptotic risk analysis; image denoising algorithm; mean-square risk; nonlocal suboptimality; piecewise constant; sharp edge discontinuity; sharp edge imaging; wavelet thresholding; Algorithm design and analysis; Image edge detection; Noise measurement; Noise reduction; Risk analysis; Smoothing methods; Upper bound;
fLanguage
English
Publisher
ieee
Conference_Titel
Communication, Control, and Computing (Allerton), 2011 49th Annual Allerton Conference on
Conference_Location
Monticello, IL
Print_ISBN
978-1-4577-1817-5
Type
conf
DOI
10.1109/Allerton.2011.6120182
Filename
6120182
Link To Document