Table of Contents

Class IntelligentScissorsMB

Namespace
OpenCvSharp.Segmentation
Assembly
OpenCvSharp.dll

Intelligent Scissors image segmentation

This class is used to find the path (contour) between two points which can be used for image segmentation.

Usage example: @snippet snippets/imgproc_segmentation.cpp usage_example_intelligent_scissors

Reference: Intelligent Scissors for Image Composition http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.138.3811&rep=rep1&type=pdf algorithm designed by Eric N. Mortensen and William A. Barrett, Brigham Young University @cite Mortensen95intelligentscissors

public class IntelligentScissorsMB : DisposableCvObject, IDisposable, ICvPtrHolder
Inheritance
IntelligentScissorsMB
Implements
Inherited Members

Constructors

IntelligentScissorsMB()

Constructor

public IntelligentScissorsMB()

Methods

ApplyImage(InputArray)

Specify input image and extract image features

public IntelligentScissorsMB ApplyImage(InputArray image)

Parameters

image InputArray

input image. Type is #CV_8UC1 / #CV_8UC3

Returns

IntelligentScissorsMB

ApplyImageFeatures(InputArray, InputArray, InputArray, InputArray?)

Specify custom features of imput image Customized advanced variant of applyImage() call.

public IntelligentScissorsMB ApplyImageFeatures(InputArray nonEdge, InputArray gradientDirection, InputArray gradientMagnitude, InputArray? image = null)

Parameters

nonEdge InputArray

Specify cost of non-edge pixels. Type is CV_8UC1. Expected values are {0, 1}.

gradientDirection InputArray

Specify gradient direction feature. Type is CV_32FC2. Values are expected to be normalized: x^2 + y^2 == 1

gradientMagnitude InputArray

Specify cost of gradient magnitude function: Type is CV_32FC1. Values should be in range [0, 1].

image InputArray

Optional parameter. Must be specified if subset of features is specified (non-specified features are calculated internally)

Returns

IntelligentScissorsMB

BuildMap(Point)

Prepares a map of optimal paths for the given source point on the image Note: applyImage() / applyImageFeatures() must be called before this call

public void BuildMap(Point sourcePt)

Parameters

sourcePt Point

The source point used to find the paths

DisposeUnmanaged()

Releases unmanaged resources

protected override void DisposeUnmanaged()

GetContour(Point, OutputArray, bool)

Extracts optimal contour for the given target point on the image Note: buildMap() must be called before this call

public void GetContour(Point targetPt, OutputArray contour, bool backward = false)

Parameters

targetPt Point

The target point

contour OutputArray

contour The list of pixels which contains optimal path between the source and the target points of the image. Type is CV_32SC2 (compatible with std::vector<Point>)

backward bool

Flag to indicate reverse order of retrived pixels (use "true" value to fetch points from the target to the source point)

SetEdgeFeatureCannyParameters(double, double, int, bool)

Switch edge feature extractor to use Canny edge detector Note: "Laplacian Zero-Crossing" feature extractor is used by default (following to original article)

public IntelligentScissorsMB SetEdgeFeatureCannyParameters(double threshold1, double threshold2, int apertureSize = 3, bool l2gradient = false)

Parameters

threshold1 double
threshold2 double
apertureSize int
l2gradient bool

Returns

IntelligentScissorsMB

SetEdgeFeatureZeroCrossingParameters(float)

Switch to "Laplacian Zero-Crossing" edge feature extractor and specify its parameters

This feature extractor is used by default according to article.

Implementation has additional filtering for regions with low-amplitude noise. This filtering is enabled through parameter of minimal gradient amplitude (use some small value 4, 8, 16).

@note Current implementation of this feature extractor is based on processing of grayscale images (color image is converted to grayscale image first).

@note Canny edge detector is a bit slower, but provides better results (especially on color images): use setEdgeFeatureCannyParameters().

public IntelligentScissorsMB SetEdgeFeatureZeroCrossingParameters(float gradientMagnitudeMinValue = 0)

Parameters

gradientMagnitudeMinValue float

Minimal gradient magnitude value for edge pixels (default: 0, check is disabled)

Returns

IntelligentScissorsMB

SetGradientMagnitudeMaxLimit(float)

Specify gradient magnitude max value threshold

Zero limit value is used to disable gradient magnitude thresholding (default behavior, as described in original article). Otherwize pixels with gradient magnitude >= threshold have zero cost.

@note Thresholding should be used for images with irregular regions (to avoid stuck on parameters from high-contract areas, like embedded logos).

public IntelligentScissorsMB SetGradientMagnitudeMaxLimit(float gradientMagnitudeThresholdMax = 0)

Parameters

gradientMagnitudeThresholdMax float

Specify gradient magnitude max value threshold (default: 0, disabled)

Returns

IntelligentScissorsMB

SetWeights(float, float, float)

Specify weights of feature functions

Consider keeping weights normalized (sum of weights equals to 1.0) Discrete dynamic programming (DP) goal is minimization of costs between pixels.

public IntelligentScissorsMB SetWeights(float weightNonEdge, float weightGradientDirection, float weightGradientMagnitude)

Parameters

weightNonEdge float

Specify cost of non-edge pixels (default: 0.43f)

weightGradientDirection float

Specify cost of gradient direction function (default: 0.43f)

weightGradientMagnitude float

Specify cost of gradient magnitude function (default: 0.14f)

Returns

IntelligentScissorsMB
Edit this page