org.opencv.imgproc

Class IntelligentScissorsMB

java.lang.Object

org.opencv.imgproc.IntelligentScissorsMB

public class IntelligentScissorsMB
extends java.lang.Object

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

Constructor Summary

Constructors

Constructor and Description
IntelligentScissorsMB()

Method Summary

Modifier and Type	Method and Description
static IntelligentScissorsMB	__fromPtr__(long addr)
IntelligentScissorsMB	applyImage(Mat image) Specify input image and extract image features
IntelligentScissorsMB	applyImageFeatures(Mat non_edge, Mat gradient_direction, Mat gradient_magnitude) Specify custom features of input image Customized advanced variant of applyImage() call.
IntelligentScissorsMB	applyImageFeatures(Mat non_edge, Mat gradient_direction, Mat gradient_magnitude, Mat image) Specify custom features of input image Customized advanced variant of applyImage() call.
void	buildMap(Point sourcePt) Prepares a map of optimal paths for the given source point on the image Note: applyImage() / applyImageFeatures() must be called before this call
void	getContour(Point targetPt, Mat contour) Extracts optimal contour for the given target point on the image Note: buildMap() must be called before this call
void	getContour(Point targetPt, Mat contour, boolean backward) Extracts optimal contour for the given target point on the image Note: buildMap() must be called before this call
long	getNativeObjAddr()
IntelligentScissorsMB	setEdgeFeatureCannyParameters(double threshold1, double threshold2) Switch edge feature extractor to use Canny edge detector Note: "Laplacian Zero-Crossing" feature extractor is used by default (following to original article) SEE: Canny
IntelligentScissorsMB	setEdgeFeatureCannyParameters(double threshold1, double threshold2, int apertureSize) Switch edge feature extractor to use Canny edge detector Note: "Laplacian Zero-Crossing" feature extractor is used by default (following to original article) SEE: Canny
IntelligentScissorsMB	setEdgeFeatureCannyParameters(double threshold1, double threshold2, int apertureSize, boolean L2gradient) Switch edge feature extractor to use Canny edge detector Note: "Laplacian Zero-Crossing" feature extractor is used by default (following to original article) SEE: Canny
IntelligentScissorsMB	setEdgeFeatureZeroCrossingParameters() Switch to "Laplacian Zero-Crossing" edge feature extractor and specify its parameters This feature extractor is used by default according to article.
IntelligentScissorsMB	setEdgeFeatureZeroCrossingParameters(float gradient_magnitude_min_value) Switch to "Laplacian Zero-Crossing" edge feature extractor and specify its parameters This feature extractor is used by default according to article.
IntelligentScissorsMB	setGradientMagnitudeMaxLimit() Specify gradient magnitude max value threshold Zero limit value is used to disable gradient magnitude thresholding (default behavior, as described in original article).
IntelligentScissorsMB	setGradientMagnitudeMaxLimit(float gradient_magnitude_threshold_max) Specify gradient magnitude max value threshold Zero limit value is used to disable gradient magnitude thresholding (default behavior, as described in original article).
IntelligentScissorsMB	setWeights(float weight_non_edge, float weight_gradient_direction, float weight_gradient_magnitude) 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.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

IntelligentScissorsMB

public IntelligentScissorsMB()

Method Detail

__fromPtr__

public static IntelligentScissorsMB __fromPtr__(long addr)

applyImage

public IntelligentScissorsMB applyImage(Mat image)

Specify input image and extract image features

Parameters:

image - input image. Type is #CV_8UC1 / #CV_8UC3

Returns:

automatically generated

applyImageFeatures

public IntelligentScissorsMB applyImageFeatures(Mat non_edge,
                                                Mat gradient_direction,
                                                Mat gradient_magnitude)

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

Parameters:

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

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

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

Returns:

automatically generated

applyImageFeatures

public IntelligentScissorsMB applyImageFeatures(Mat non_edge,
                                                Mat gradient_direction,
                                                Mat gradient_magnitude,
                                                Mat image)

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

Parameters:

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

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

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

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

Returns:

automatically generated

buildMap

public void buildMap(Point sourcePt)

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

Parameters:

sourcePt - The source point used to find the paths

getContour

public void getContour(Point targetPt,
                       Mat contour)

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

Parameters:

targetPt - The target point

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>)

getContour

public void getContour(Point targetPt,
                       Mat contour,
                       boolean backward)

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

Parameters:

targetPt - The target point

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

getNativeObjAddr

public long getNativeObjAddr()

setEdgeFeatureCannyParameters

public IntelligentScissorsMB setEdgeFeatureCannyParameters(double threshold1,
                                                           double threshold2)

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

Parameters:

threshold1 - automatically generated

threshold2 - automatically generated

Returns:

automatically generated

setEdgeFeatureCannyParameters

public IntelligentScissorsMB setEdgeFeatureCannyParameters(double threshold1,
                                                           double threshold2,
                                                           int apertureSize)

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

Parameters:

threshold1 - automatically generated

threshold2 - automatically generated

apertureSize - automatically generated

Returns:

automatically generated

setEdgeFeatureCannyParameters

public IntelligentScissorsMB setEdgeFeatureCannyParameters(double threshold1,
                                                           double threshold2,
                                                           int apertureSize,
                                                           boolean L2gradient)

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

Parameters:

threshold1 - automatically generated

threshold2 - automatically generated

apertureSize - automatically generated

L2gradient - automatically generated

Returns:

automatically generated

setEdgeFeatureZeroCrossingParameters

public IntelligentScissorsMB setEdgeFeatureZeroCrossingParameters()

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().

Returns:

automatically generated

setEdgeFeatureZeroCrossingParameters

public IntelligentScissorsMB setEdgeFeatureZeroCrossingParameters(float gradient_magnitude_min_value)

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().

Parameters:

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

Returns:

automatically generated

setGradientMagnitudeMaxLimit

public IntelligentScissorsMB setGradientMagnitudeMaxLimit()

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).

Returns:

automatically generated

setGradientMagnitudeMaxLimit

public IntelligentScissorsMB setGradientMagnitudeMaxLimit(float gradient_magnitude_threshold_max)

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).

Parameters:

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

Returns:

automatically generated

setWeights

public IntelligentScissorsMB setWeights(float weight_non_edge,
                                        float weight_gradient_direction,
                                        float weight_gradient_magnitude)

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.

Parameters:

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

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

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

Returns:

automatically generated