Share Email Print
cover

Proceedings Paper

Higher order bilateral filters and their properties
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Bilateral filtering1, 2 has proven to be a powerful tool for adaptive denoising purposes. Unlike conventional filters, the bilateral filter defines the closeness of two pixels not only based on geometric distance but also based on radiometric (graylevel) distance. In this paper, to further improve the performance and find new applications, we make contact with a classic non-parametric image reconstruction technique called kernel regression,3 which is based on local Taylor expansions of the regression function. We extend and generalize the kernel regression method and show that bilateral filtering is a special case of this new class of adaptive image reconstruction techniques, considering a specific choice for weighting kernels and zeroth order Taylor approximation. We show improvements over the classic bilateral filtering can be achieved by using higher order local approximations of the signal.

Paper Details

Date Published: 28 February 2007
PDF: 9 pages
Proc. SPIE 6498, Computational Imaging V, 64980S (28 February 2007); doi: 10.1117/12.714507
Show Author Affiliations
Hiroyuki Takeda, Univ. of California, Santa Cruz (United States)
Sina Farsiu, Univ. of California, Santa Cruz (United States)
Peyman Milanfar, Univ. of California, Santa Cruz (United States)


Published in SPIE Proceedings Vol. 6498:
Computational Imaging V
Charles A. Bouman; Eric L. Miller; Ilya Pollak, Editor(s)

© SPIE. Terms of Use
Back to Top