en>Jay1279: Wikified as part of the Wikification WikiProject!

2010-10-04T03:00:11Z

Wikified as part of the Wikification WikiProject!

New page

A '''bilateral filter''' is non-linear, edge-preserving and [[noise reduction|noise-reducing]] [[smoothing]] [[Digital image processing|filter for images]]. The intensity value at each pixel in an image is replaced by a weighted average of intensity values from nearby pixels. This weight can be based on a Gaussian distribution. Crucially, the weights depend not only on Euclidean distance of pixels, but also on the radiometric differences. For example, the range difference such as color intensity, depth distance, etc. This preserves sharp edges by systematically looping through each pixel and adjusting weights to the adjacent pixels accordingly.

The bilateral filter is defined as

<math>
I^\text{filtered}(x) = \frac{1}{W_p} \sum_{x_i \in \Omega} I(x_i)f_r(\|I(x_i)-I(x)\|)g_s(\|x_i-x\|),
</math>

where the normalization term

<math>
W_p = \sum_{x_i \in \Omega}{f_r(\|I(x_i)-I(x)\|)g_s(\|x_i-x\|)}
</math>

ensures that the filter preserves image energy and

* <math>I^\text{filtered} </math> is the filtered image;
* <math>I</math> is the original input image to be filtered;
* <math>x</math> are the coordinates of the current pixel to be filtered;
* <math>\Omega</math> is the window centered in <math>x</math>;
* <math>f_r</math> is the range kernel for smoothing differences in intensities. This function can be a Gaussian function;
* <math>g_s</math> is the spatial kernel for smoothing differences in coordinates. This function can be a Gaussian function;

[[Adobe Photoshop]] implements a bilateral filter in its ''surface blur'' tool. [[GIMP]] implements a bilateral filter in its ''Filters-->Blur'' tools; and it is called ''Selective Gaussian Blur'''.

== See also ==
* [[Gaussian filter]]
* [[Gaussian function]]
* [[Gaussian blur]]
* [[Convolution]]

== External links ==
* Kunal N. Chaudhury [https://sites.google.com/site/kunalnchaudhury/Publications/journals/manuscript.pdf Constant-time filtering]
* Kunal N. Chaudhury, Daniel Sage, and Michael Unser [http://bigwww.epfl.ch/algorithms/bilateral-filter/ Java plugin], [http://bigwww.epfl.ch/chaudhury/Fast%20bilateral%20filtering.pdf Fast bilateral filtering]
* Haarith Devarajan, Harold Nyikal, [http://scien.stanford.edu/pages/labsite/2006/psych221/projects/06/imagescaling/bilati.html Bilateral Filters], in: [http://scien.stanford.edu/pages/labsite/2006/psych221/projects/06/imagescaling/ Image Scaling and Bilateral Filtering] 2006 course
* Sylvain Paris, Pierre Kornprobst, Jack Tumblin, Frédo Durand, [http://dx.doi.org/10.1561/0600000020 Bilateral Filtering: Theory and Applications], [http://people.csail.mit.edu/sparis/#fntcgv preprint]
* Sylvain Paris, Pierre Kornprobst, Jack Tumblin, Frédo Durand, [http://people.csail.mit.edu/sparis/bf_course/ A Gentle Introduction to Bilateral Filtering and its Applications], [http://www.siggraph.org/s2008/ SIGGRAPH 2008] class
* Ben Weiss, [http://www.shellandslate.com/download/fastmedian_5506.pdf Fast Median and Bilateral Filtering], [http://www.siggraph.org/s2006/ SIGGRAPH 2006] preprint
* Carlo Tomasi, Roberto Manduchi, [http://www.cse.ucsc.edu/~manduchi/Papers/ICCV98.pdf Bilateral Filtering for Gray and Color Images] (shorter [http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/MANDUCHI1/Bilateral_Filtering.html HTML] version), proceedings of the [http://www.umiacs.umd.edu/users/lsd/iccv/ ICCV 1998]

{{technology-stub}}

[[Category:Nonlinear filters]]

Window operator - Revision history

en>Jay1279: Wikified as part of the Wikification WikiProject!