Intelligent Scissors image segmentation [詳解]

#include <segmentation.hpp>

公開メンバ関数
CV_WRAP IntelligentScissorsMB &	setWeights (float weight_non_edge, float weight_gradient_direction, float weight_gradient_magnitude)
	Specify weights of feature functions [詳解]

CV_WRAP IntelligentScissorsMB &	setGradientMagnitudeMaxLimit (float gradient_magnitude_threshold_max=0.0f)
	Specify gradient magnitude max value threshold [詳解]

CV_WRAP IntelligentScissorsMB &	setEdgeFeatureZeroCrossingParameters (float gradient_magnitude_min_value=0.0f)
	Switch to "Laplacian Zero-Crossing" edge feature extractor and specify its parameters [詳解]

CV_WRAP IntelligentScissorsMB &	setEdgeFeatureCannyParameters (double threshold1, double threshold2, int apertureSize=3, bool L2gradient=false)
	Switch edge feature extractor to use Canny edge detector [詳解]

CV_WRAP IntelligentScissorsMB &	applyImage (InputArray image)
	Specify input image and extract image features [詳解]

CV_WRAP IntelligentScissorsMB &	applyImageFeatures (InputArray non_edge, InputArray gradient_direction, InputArray gradient_magnitude, InputArray image=noArray())
	Specify custom features of imput image [詳解]

CV_WRAP void	buildMap (const Point &sourcePt)
	Prepares a map of optimal paths for the given source point on the image [詳解]

CV_WRAP void	getContour (const Point &targetPt, OutputArray contour, bool backward=false) const
	Extracts optimal contour for the given target point on the image [詳解]

Impl *	getImpl () const

限定公開変数類
std::shared_ptr< Impl >	impl

詳解

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:

Reference: "Intelligent Scissors for Image Composition" algorithm designed by Eric N. Mortensen and William A. Barrett, Brigham Young University [Mortensen95intelligentscissors]

関数詳解

◆ applyImage()

CV_WRAP IntelligentScissorsMB & cv::segmentation::IntelligentScissorsMB::applyImage ( InputArray image )

Specify input image and extract image features

引数

image input image. Type is #CV_8UC1 / #CV_8UC3

◆ applyImageFeatures()

CV_WRAP IntelligentScissorsMB & cv::segmentation::IntelligentScissorsMB::applyImageFeatures	(	InputArray	non_edge,
		InputArray	gradient_direction,
		InputArray	gradient_magnitude,
		InputArray	image = `noArray()`
	)

Specify custom features of imput image

Customized advanced variant of applyImage() call.

引数

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)

◆ buildMap()

CV_WRAP void cv::segmentation::IntelligentScissorsMB::buildMap ( const Point & sourcePt )

Prepares a map of optimal paths for the given source point on the image

覚え書き: applyImage() / applyImageFeatures() must be called before this call

引数

sourcePt The source point used to find the paths

◆ getContour()

CV_WRAP void cv::segmentation::IntelligentScissorsMB::getContour	(	const Point &	targetPt,
		OutputArray	contour,
		bool	backward = `false`
	)		const

Extracts optimal contour for the given target point on the image

覚え書き: buildMap() must be called before this call

引数

	targetPt	The target point
[out]	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)

◆ setEdgeFeatureCannyParameters()

CV_WRAP IntelligentScissorsMB & cv::segmentation::IntelligentScissorsMB::setEdgeFeatureCannyParameters	(	double	threshold1,
		double	threshold2,
		int	apertureSize = `3`,
		bool	L2gradient = `false`
	)

Switch edge feature extractor to use Canny edge detector

覚え書き: "Laplacian Zero-Crossing" feature extractor is used by default (following to original article)

参照: Canny

◆ setEdgeFeatureZeroCrossingParameters()

CV_WRAP IntelligentScissorsMB & cv::segmentation::IntelligentScissorsMB::setEdgeFeatureZeroCrossingParameters ( float gradient_magnitude_min_value = 0.0f )

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).

覚え書き: Current implementation of this feature extractor is based on processing of grayscale images (color image is converted to grayscale image first).; Canny edge detector is a bit slower, but provides better results (especially on color images): use setEdgeFeatureCannyParameters().

引数

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

◆ setGradientMagnitudeMaxLimit()

CV_WRAP IntelligentScissorsMB & cv::segmentation::IntelligentScissorsMB::setGradientMagnitudeMaxLimit ( float gradient_magnitude_threshold_max = 0.0f )

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.

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

引数

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

◆ setWeights()

CV_WRAP IntelligentScissorsMB & cv::segmentation::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.

引数

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)

このクラス詳解は次のファイルから抽出されました:

imgproc/segmentation.hpp

公開メンバ関数

限定公開変数類

詳解

関数詳解

◆ applyImage()

◆ applyImageFeatures()

◆ buildMap()

◆ getContour()

◆ setEdgeFeatureCannyParameters()

◆ setEdgeFeatureZeroCrossingParameters()

◆ setGradientMagnitudeMaxLimit()

◆ setWeights()