Sobel3D¶
-
MLModule
¶ genre Kernel
author MeVis Medical Solutions AG
package MeVisLab/Standard
dll MLKernel
definition MLKernel.def see also Convolution
,ExtendedConvolution
,KernelEditor
keywords edge
,detect
,kernel
,filter
,interval
,gradient
,ExtendedConvolution
,Convolution
,Roberts
Purpose¶
The module Sobel3D
computes gradients of a grey-value image by applying a Sobel kernel for each main axis direction.
The module can also compute the gradients strengths and a gradient vector image.
Output Fields¶
Parameter Fields¶
Field Index¶
autoCalcMinMax : Bool |
Min. Threshold : Float |
useMinMax : Bool |
Border Handling : Enum |
Non Edge Value : Float |
|
Edge Value : Float |
outputMax : Double |
|
Fill Value : Double |
outputMin : Double |
|
Filter Mode : Enum |
referenceExtentMode : Enum |
|
Max : Double |
Scale with voxel size : Bool |
|
Max. Threshold : Float |
setAutoMinMax : Trigger |
|
Min : Double |
Use : Bool |
Visible Fields¶
Border Handling¶
-
name:
borderHandling
, type:
Enum
, default:
PadSrcClamp
, deprecated name:
edgeMode
¶ Defines the border handling mode.
See
Border Handling in Kernel Operations
for details.
Values:
Title | Name |
---|---|
No Pad | NoPad |
Pad Src Fill | PadSrcFill |
Pad Dst Fill | PadDstFill |
Pad Dst Fill With Orig | PadDstFillWithOrig |
Pad Src Undefined | PadSrcUndefined |
Pad Dst Undefined | PadDstUndefined |
Pad Src Clamp | PadSrcClamp |
Fill Value¶
-
name:
fillValue
, type:
Double
, default:
0
¶ Sets the fill value for certain
Border Handling
modes.
Min¶
-
name:
intervalMinOfFilteredVoxels
, type:
Double
, default:
30
, deprecated name:
imageIntervalMin
¶ Sets the minimum value threshold for outputting a subset of voxel.
Max¶
-
name:
intervalMaxOfFilteredVoxels
, type:
Double
, default:
50
, deprecated name:
imageIntervalMax
¶ Sets the maximum value threshold for outputting a subset of voxel.
Use¶
-
name:
useIntervalOfFilteredVoxels
, type:
Bool
, default:
FALSE
¶ If checked, the module outputs only on a subset of voxels defined by a value range.
Min. Threshold¶
-
name:
edgeThresholdMinimum
, type:
Float
, default:
31.25
, minimum:
0
, maximum:
150000
, deprecated name:
edgeThresholdMinimumFld
¶ Set the minimum value of one kernel convolution result for thresholding in Edge Detection or in Estimation mode.
Max. Threshold¶
-
name:
edgeThresholdMaximum
, type:
Float
, default:
46.875
, minimum:
0
, maximum:
150000
, deprecated name:
edgeThresholdMaximumFld
¶ Set the maximum value of one kernel convolution result for thresholding in Edge Detection or in Estimation mode.
Edge Value¶
-
name:
detectedEdgeValue
, type:
Float
, default:
32
, minimum:
0
, maximum:
4096
, deprecated name:
detectedEdgeValueFld
¶ If in Edge Detection mode, this value will be set into the output image when the convolution value lies within the threshold range.
Non Edge Value¶
-
name:
detectedNonEdgeValue
, type:
Float
, default:
0
, minimum:
0
, maximum:
4096
, deprecated name:
detectedNonEdgeValueFld
¶ If in Edge Detection mode, this value will be set into the output image when the convolution value lies outside of the threshold value.
Scale with voxel size¶
-
name:
useVoxelSize
, type:
Bool
, default:
TRUE
¶ If checked and in Gradient Strength mode, each resulting convolution value is divided by the voxel size in the particular (xyz) direction.
Filter Mode¶
-
name:
filterMode
, type:
Enum
, default:
Gradient Strength
, deprecated name:
FilterMode
¶ Sets the filter mode of this module.
Values:
Title | Name | Description |
---|---|---|
Gradient Strength | Gradient Strength | The resulting sum of the kernel convolutions is written into the ouput image, which is a grey-value image representing the strengths of the gradients in each voxel. |
Edge Detection | Edge Detection | Thresholds the convolution values in each direction: if any of these values is within the threshold range, an Edge Value is written into the output image, a Non Edge Value is written else, resulting in a binary edge image. |
Estimation | Estimation | The values of the three convolutions are used as vector components, where the x,y,z values are coded into r,g,b values of the output image, resulting in a RGB-image. |
Gradient Estimation And Strength Packed | GradientEstimationAndStrengthPacked | Estimates the gradient and its strength. The gradient and strength are normalized and packed to the range 0-1 using: rgb = (grad / gradStrength + 1.) * 0.5
a = gradStrength / maxGradStrength
This is the format that makes it usable for the GVR and SoPathTracer, since they will convert this input gradient image to RGBA8 and have the same packing convention. |