opencv grabcut 分割算法

grabcut基于论文"GrabCut" - Interactive Foreground Extraction using Iterated Graph Cuts，是微软亚洲研究院04年的论文。

本代码摘自opencv的示例代码，自己做了一些修改，加入了一个输出mask的功能。另外，由于grabcut会造成不少小洞，所以还加入了了一个轮廓检测模块。但这样会导致最外层的一层像素显示不出来。

detect.h:

//本程序的目的是检测mask

//缺点： 1， 会造成边界有一个像素丢失
//2， 会造成obj中间的洞检测不出来

#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
using namespace cv;

#include <iostream>
using namespace std;


int GetMaxContour(vector<vector<Point> > contours)
{
	assert(contours.size() > 0);

	int i = contours.size();

	if (i == 1)
	{
		return 0;
	}
	else
	{
		int result = 0;

		for (int j = 1; j < i; j++)
		{
			if (contours[j].size() > contours[result].size())
				result = j;
		}

		return result;
	}
}

Mat GetMask(Mat mask, Vec3b color)
{
	assert(mask.type() == CV_8UC1);

	vector<vector<Point> > contours;
	vector<Vec4i> hierarchy;

	findContours(mask.clone(), contours, hierarchy, CV_RETR_TREE,
			 CV_CHAIN_APPROX_NONE, Point(0, 0));

	Mat mask_ray = Mat(mask.size(), CV_8UC1, Scalar::all(0));

	drawContours(mask_ray, contours, GetMaxContour(contours), Scalar::all(255),
			 CV_FILLED, 8, hierarchy, 0);

	Mat result = Mat(mask.size(), CV_8UC3, Scalar::all(0));

	for (int i = 0; i< mask.rows; i++)
		for (int j = 0;j< mask.cols; j++)
			if (mask_ray.at<uchar>(i, j) == 255)
				result.at<Vec3b>(i, j) = color;

	return result;
}

grabcut.cpp:

//本程序的目的是测试grabcut算法

#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
using namespace cv;

#include <iostream>
using namespace std;

#include "detect.h"

static void help()
{
	cout << "\nThis program demonstrates GrabCut segmentation -- select an object in a region\n"
		"and then grabcut will attempt to segment it out.\n"
		"Call:\n"
		"./grabcut <image_name>\n"
		"\nSelect a rectangular area around the object you want to segment\n" <<
		"\nHot keys: \n"
		"\tESC - quit the program\n"
		"\tr - restore the original image\n"
		"\tn - next iteration\n"
		"\n"
		"\tleft mouse button - set rectangle\n"
		"\n"
		"\tCTRL+left mouse button - set GC_BGD pixels\n"
		"\tSHIFT+left mouse button - set CG_FGD pixels\n"
		"\n"
		"\tCTRL+right mouse button - set GC_PR_BGD pixels\n"
		"\tSHIFT+right mouse button - set CG_PR_FGD pixels\n" << endl;
}

const Scalar RED = Scalar(0,0,255);
const Scalar PINK = Scalar(230,130,255);
const Scalar BLUE = Scalar(255,0,0);
const Scalar LIGHTBLUE = Scalar(255,255,160);
const Scalar GREEN = Scalar(0,255,0);

const int BGD_KEY = CV_EVENT_FLAG_CTRLKEY;
const int FGD_KEY = CV_EVENT_FLAG_SHIFTKEY;

Mat finalmask;

static void getBinMask( const Mat& comMask, Mat& binMask )
{
	if( comMask.empty() || comMask.type()!=CV_8UC1 )
		CV_Error( CV_StsBadArg, "comMask is empty or has incorrect type (not CV_8UC1)" );
	if( binMask.empty() || binMask.rows!=comMask.rows || binMask.cols!=comMask.cols )
		binMask.create( comMask.size(), CV_8UC1 );
	binMask = comMask & 1;
}

class GCApplication
{
public:
	enum{ NOT_SET = 0, IN_PROCESS = 1, SET = 2 };
	static const int radius = 2;
	static const int thickness = -1;

	void reset();
	void setImageAndWinName( const Mat& _image, const string& _winName );
	void showImage() const;
	void write();
	void mouseClick( int event, int x, int y, int flags, void* param );
	int nextIter();
	int getIterCount() const { return iterCount; }
private:
	void setRectInMask();
	void setLblsInMask( int flags, Point p, bool isPr );

	const string* winName;
	const Mat* image;
	Mat mask;
	Mat bgdModel, fgdModel;

	uchar rectState, lblsState, prLblsState;
	bool isInitialized;

	Rect rect;
	vector<Point> fgdPxls, bgdPxls, prFgdPxls, prBgdPxls;
	int iterCount;
};

void GCApplication::reset()
{
	if( !mask.empty() )
		mask.setTo(Scalar::all(GC_BGD));
	bgdPxls.clear(); fgdPxls.clear();
	prBgdPxls.clear();  prFgdPxls.clear();

	isInitialized = false;
	rectState = NOT_SET;
	lblsState = NOT_SET;
	prLblsState = NOT_SET;
	iterCount = 0;
}

void GCApplication::setImageAndWinName( const Mat& _image, const string& _winName  )
{
	if( _image.empty() || _winName.empty() )
		return;
	image = &_image;
	winName = &_winName;
	mask.create( image->size(), CV_8UC1);
	reset();
}

void GCApplication::showImage() const
{
	if( image->empty() || winName->empty() )
		return;

	Mat res;
	Mat binMask;
	if( !isInitialized )
		image->copyTo( res );
	else
	{
		getBinMask( mask, binMask );
		image->copyTo( res, binMask );
	}

	vector<Point>::const_iterator it;
	for( it = bgdPxls.begin(); it != bgdPxls.end(); ++it )
		circle( res, *it, radius, BLUE, thickness );
	for( it = fgdPxls.begin(); it != fgdPxls.end(); ++it )
		circle( res, *it, radius, RED, thickness );
	for( it = prBgdPxls.begin(); it != prBgdPxls.end(); ++it )
		circle( res, *it, radius, LIGHTBLUE, thickness );
	for( it = prFgdPxls.begin(); it != prFgdPxls.end(); ++it )
		circle( res, *it, radius, PINK, thickness );

	if( rectState == IN_PROCESS || rectState == SET )
		rectangle( res, Point( rect.x, rect.y ), Point(rect.x + rect.width, rect.y + rect.height ), GREEN, 2);

	imshow( *winName, res );
}

void GCApplication::write()
{
	Mat binMask;

	getBinMask( mask, binMask );

	Vec3b color = Vec3b((uchar)rand(), (uchar)rand(), (uchar)rand());

	Mat tmpmask = GetMask(binMask, color);

	for (int i = 0; i< mask.rows; i++)
		for (int j = 0;j< mask.cols; j++)
			if (tmpmask.at<Vec3b>(i, j) == color)
				finalmask.at<Vec3b>(i, j) = color;

	//finalmask += GetMask(binMask, color);

	imshow( "mask", finalmask );
}

void GCApplication::setRectInMask()
{
	assert( !mask.empty() );
	mask.setTo( GC_BGD );
	rect.x = max(0, rect.x);
	rect.y = max(0, rect.y);
	rect.width = min(rect.width, image->cols-rect.x);
	rect.height = min(rect.height, image->rows-rect.y);
	(mask(rect)).setTo( Scalar(GC_PR_FGD) );
}

void GCApplication::setLblsInMask( int flags, Point p, bool isPr )
{
	vector<Point> *bpxls, *fpxls;
	uchar bvalue, fvalue;
	if( !isPr )
	{
		bpxls = &bgdPxls;
		fpxls = &fgdPxls;
		bvalue = GC_BGD;
		fvalue = GC_FGD;
	}
	else
	{
		bpxls = &prBgdPxls;
		fpxls = &prFgdPxls;
		bvalue = GC_PR_BGD;
		fvalue = GC_PR_FGD;
	}
	if( flags & BGD_KEY )
	{
		bpxls->push_back(p);
		circle( mask, p, radius, bvalue, thickness );
	}
	if( flags & FGD_KEY )
	{
		fpxls->push_back(p);
		circle( mask, p, radius, fvalue, thickness );
	}
}

void GCApplication::mouseClick( int event, int x, int y, int flags, void* )
{
	// TODO add bad args check
	switch( event )
	{
	case CV_EVENT_LBUTTONDOWN: // set rect or GC_BGD(GC_FGD) labels
		{
			bool isb = (flags & BGD_KEY) != 0,
				isf = (flags & FGD_KEY) != 0;
			if( rectState == NOT_SET && !isb && !isf )
			{
				rectState = IN_PROCESS;
				rect = Rect( x, y, 1, 1 );
			}
			if ( (isb || isf) && rectState == SET )
				lblsState = IN_PROCESS;
		}
		break;
	case CV_EVENT_RBUTTONDOWN: // set GC_PR_BGD(GC_PR_FGD) labels
		{
			bool isb = (flags & BGD_KEY) != 0,
				isf = (flags & FGD_KEY) != 0;
			if ( (isb || isf) && rectState == SET )
				prLblsState = IN_PROCESS;
		}
		break;
	case CV_EVENT_LBUTTONUP:
		if( rectState == IN_PROCESS )
		{
			rect = Rect( Point(rect.x, rect.y), Point(x,y) );
			rectState = SET;
			setRectInMask();
			assert( bgdPxls.empty() && fgdPxls.empty() && prBgdPxls.empty() && prFgdPxls.empty() );
			showImage();
		}
		if( lblsState == IN_PROCESS )
		{
			setLblsInMask(flags, Point(x,y), false);
			lblsState = SET;
			showImage();
		}
		break;
	case CV_EVENT_RBUTTONUP:
		if( prLblsState == IN_PROCESS )
		{
			setLblsInMask(flags, Point(x,y), true);
			prLblsState = SET;
			showImage();
		}
		break;
	case CV_EVENT_MOUSEMOVE:
		if( rectState == IN_PROCESS )
		{
			rect = Rect( Point(rect.x, rect.y), Point(x,y) );
			assert( bgdPxls.empty() && fgdPxls.empty() && prBgdPxls.empty() && prFgdPxls.empty() );
			showImage();
		}
		else if( lblsState == IN_PROCESS )
		{
			setLblsInMask(flags, Point(x,y), false);
			showImage();
		}
		else if( prLblsState == IN_PROCESS )
		{
			setLblsInMask(flags, Point(x,y), true);
			showImage();
		}
		break;
	}
}

int GCApplication::nextIter()
{
	if( isInitialized )
		grabCut( *image, mask, rect, bgdModel, fgdModel, 1 );
	else
	{
		if( rectState != SET )
			return iterCount;

		if( lblsState == SET || prLblsState == SET )
			grabCut( *image, mask, rect, bgdModel, fgdModel, 1, GC_INIT_WITH_MASK );
		else
			grabCut( *image, mask, rect, bgdModel, fgdModel, 1, GC_INIT_WITH_RECT );

		isInitialized = true;
	}
	iterCount++;

	bgdPxls.clear(); fgdPxls.clear();
	prBgdPxls.clear(); prFgdPxls.clear();

	return iterCount;
}

GCApplication gcapp;

static void on_mouse( int event, int x, int y, int flags, void* param )
{
	gcapp.mouseClick( event, x, y, flags, param );
}

int main( int argc, char** argv )
{
	string name = "stove";
	string filename = "input/"+name+".jpg";
	string resultname = "output/"+name+".png";
	if( filename.empty() )
	{
		cout << "\nDurn, couldn't read in " << argv[1] << endl;
		return 1;
	}
	Mat image = imread( filename, 1 );
	if( image.empty() )
	{
		cout << "\n Durn, couldn't read image filename " << filename << endl;
		return 1;
	}

	help();

	Mat src = image.clone();
	imshow("Src", src);

	finalmask = Mat::zeros(src.size(), CV_8UC3);

	const string winName = "image";
	cvNamedWindow( winName.c_str(), CV_WINDOW_AUTOSIZE );
	cvSetMouseCallback( winName.c_str(), on_mouse, 0 );

	gcapp.setImageAndWinName( image, winName );
	gcapp.showImage();

	for(;;)
	{
		int c = cvWaitKey(0);
		switch( (char) c )
		{
		case '\x1b':
			{
				cout << "Exiting ..." << endl;
				goto exit_main;
			}
		case 'r':
			{
				cout << endl;
				gcapp.reset();
				gcapp.showImage();
				break;
			}
		case 'n':
			{
				int iterCount = gcapp.getIterCount();
				cout << "<" << iterCount << "... ";
				int newIterCount = gcapp.nextIter();
				if( newIterCount > iterCount )
				{
					gcapp.showImage();
					cout << iterCount << ">" << endl;
				}
				else
					cout << "rect must be determined>" << endl;
				break;
			}
		case 'w':
			{
				gcapp.write();
				break;
			}
		}
	}

exit_main:
	{
		imwrite(resultname, finalmask);
		cvDestroyWindow( winName.c_str() );
		return 0;
	}
}

最后，opencv的效果和原文有一定差距。这是因为原文加入了border matting的技术，而因为专利权的原因，opencv没有加。