Roberts

MLModule

genre

Kernel

author

MeVis Medical Solutions AG

package

MeVisLab/Standard

dll

MLKernel

definition

MLKernel.def

see also

ExtendedConvolution, Compass, Convolution, KernelExample, TextureFilter, Morphology, BitMorphology

keywords

filter, Cross, edge, detection

Purpose

The module Roberts implements different variations of the Roberts filter.

Windows

Default Panel

../../../Modules/ML/MLKernel/mhelp/Images/Screenshots/Roberts._default.png

Input Fields

input0

name: input0, type: Image

Output Fields

output0

name: output0, type: Image

Parameter Fields

Field Index

Border Handling: Enum

Fill Value: Double

Max: Double

Min: Double

referenceExtentMode: Enum

Roberts Operator: Enum

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.

Roberts Operator

name: robertsOperator, type: Enum, default: Roberts2 (square)

Defines the filter mode.

Values:

Title

Name

Description

​Roberts2 (one direction - x)

​Roberts2 (one direction - x)

​Roberts Cross in only one direction (x) with:

1  0
0 -1

​Roberts2 (one direction - y)

​Roberts2 (one direction - y)

​Roberts Cross in only one direction (y) with:

0 -1
1  0

​Roberts2 (standard)

​Roberts2 (standard)

​Standard Roberts Cross with:

1 -1
1 -1

​Roberts2 (absolute values)

​Roberts2 (absolute values)

​Roberts Cross. Let (a, b, c, d) be the voxel values below the following kernel:

a  b
c  d

The result voxel is

abs(a-d) + abs(c-b)

​Roberts2 (square)

​Roberts2 (square)

​Roberts Cross. Let (a, b, c, d) be the voxel values below the following kernel:

a  b
c  d

The result voxel is

sqrt((a-d)*(a-d) + (c-b)*(c-b))

​Roberts6 (absolute values)

​Roberts6 (absolute values)

​Roberts Cross like Roberts2, but using all 6 pairwise differences:

Let (a,b,c,d) be the voxel values below the following kernel:

a  b
c  d

The result voxel is

1.0f/3.0f * (abs(a-d) + abs(c-b) + abs(a-b) +
             abs(a-c) + abs(b-d) + abs(c-d))

​Roberts6 (square)

​Roberts6 (square)

​Roberts Cross like Robert2, but using all 6 pairwise differences.

Let (a,b,c,d) be the voxel values below the following kernel:

a  b
c  d

The result voxel is

1.0f/3.0f * sqrt((a-d)*(a-d) + (c-b)*(c-b) +
                 (a-b)*(a-b) + (a-c)*(a-c) +
                 (b-d)*(b-d) + (c-d)*(c-d))

Min

name: intervalMinOfFilteredVoxels, type: Double, default: 0, deprecated name: imageIntervalMin

Sets the minimum value threshold for outputting a subset of voxels.

Max

name: intervalMaxOfFilteredVoxels, type: Double, default: 1024, deprecated name: imageIntervalMax

Sets the maximum value threshold for outputting a subset of voxels.

Use

name: useIntervalOfFilteredVoxels, type: Bool, default: FALSE, deprecated name: useImageInterval

If checked, the module outputs only on a subset of voxels defined by a value range.

Hidden Fields

referenceExtentMode

name: referenceExtentMode, type: Enum, default: Overlap

Values:

Title

Name

​Overlap

​Overlap

​Input0 Ext Without Fill

​Input0_ExtWithoutFill

​Input0 Ext With Fill

​Input0_ExtWithFill

​Max Extents Without Fill

​MaxExtentsWithoutFill

​Max Extents With Fill

​MaxExtentsWithFill