mrcImageBilateralFilter
mrcImageBilateralFilter is Eos's Command that performs smoothing mrcImage file. It is a method for proposed by Tomasi and Manduchi, to smooth while maintaining the edge. It is a smoothing of weighted by the intensity difference of the image. Since weights are calculated by Gauss distribution for the two deviations(intensity difference, distance), region in which intensity difference is maintained without blurred.
Contents
Algorithm
It has two weights Wx(xi, xj) and WI(Ii,Ij), they are defined as such Lorenz function or Gaussian function of |xi-xj|, |Ii-Ij|. That is because the difference between the image becomes large near the edges、weight of Smoothing in density band that themselves belong is applied to them.
Failed to parse (Missing <code>texvc</code> executable. Please see math/README to configure.):
fi = Sigma_j(W(i,j)*Ij)/ Sigma_j(Wj)
,where W(i,j)=W_x(xi,xj)*W_I(Ii,Ij)
------- linfo.mode : 0
W_x(xi,xj) = exp(-|xi-xj|^2/2 sigmaSpace^2 )
W_I(Ii,Ij) = exp(-|Ii-Ij|^2/2 sigmaDensity^2)
------- linfo.mode : 1
W_x(xi,xj) = 1/(1+|xi-xj|^2/sigmaSpace^2 )
W_I(Ii,Ij) = 1/(1+|Ii-Ij|^2/sigmaDensity^2)
List of option
Main option
| Option | Essential/Optional | Description | Default |
|---|---|---|---|
| -i | Essential | Input：mrcImage | NULL |
| -o | Optional | Output：mrcImage | stdout(The standard output by default） |
| -sD | Optional | SigmaDensity(float) [ImageAmplitude] | 2.0 |
| -kTD | Optional | Kernel Type of Density (int) | 0 |
| -sS | Optional | SigmaSpace(float) [pixel] | 1.0 |
| -sS3 | Optional | SigmaSpace 3D (x:float, y:float, z:float) [pixel] | 1.0 1.0 1.0 |
| -kTS | Optional | Kernel Type of Space (int) | 0 |
| -kS | Optional | Kernel Size (int) [pixel] | 1.0 |
| -kS3 | Optional | Kernel Size 3D (x:int, y:int, z:int) [pixel] | 1.0 1.0 1.0 |
| -c | Optional | ConfigurationFile | NULL |
| -m | Optional | Mode | 0 |
| -h | Optional | Help |
-m details
| Value | Description |
|---|---|
| 0 |
-kTD details
| Value | Description |
|---|---|
| 0 | Gaussian function |
| 1 | Lorenz function |
-kTS details
| Value | Description |
|---|---|
| 0 | Gaussian function |
| 1 | Lorenz function |
Execution example
Input file(2D) image
 |
Min Max |
-18651.7 (10, 1, 0) 52942.7 (24, 39, 0) |
Example of options only essential
 |
Min Max |
-18651.7 (10, 1, 0) 52942.7 (24, 39, 0) |
Option -sD
Case: sD=50000
 |
Min Max |
-3963.33 (76, 66, 0) 36164.2 (26, 29, 0) |
Option -kTD
Case: kTD=1
 |
Min Max |
-4063.09 (56, 4, 0) 36357.6 (26, 29, 0) |
Option -sS
Case: sS=10
 |
Min Max |
-3196.78 (38, 0, 0) 32196.3 (25, 39, 0) |
Option -kTS
Case: kTS=1, sS=10
 |
Min Max |
-3198.73 (38, 0, 0) 32222.2 (25, 39, 0) |
Option -kS
Case: kS=10
 |
Min Max |
-3871.71 (76, 66, 0) 35969.2 (26, 29, 0) |
Input file(3D) image
|
|
Min Max |
-2390.42 (77, 14, 69) 4374.62 (17, 62, 46) |
Option -sD
Case: sD=1000
|
|
Min Max |
-1272.88 (77, 14, 69) 4131.48 (17, 62, 46) |
Option -sS3
Case: sS3=(1, 0.7, 1)
|
|
Min Max |
-1459.87 (77, 14, 69) 4154.41 (17, 62, 46) |
Option -kS3
Case: kS3=(2, 2, 1)
|
|
Min Max |
-1966.48 (78, 4, 26) 4354.27 (17, 62, 46) |
References
- C. Tomasi and R. Manduchi, Bilateral Filtering for Gray and Color Images, Proceedings of the 1998 IEEE International Conference on Computer Vision, Bombay, India
