用opencv检测convexity defects

 一 概念：

Convexity hull, Convexity defects

 

 

 

如上图所示，黑色的轮廓线为convexity hull, 而convexity hull与手掌之间的部分为convexity defects. 每个convexity defect区域有四个特征量：起始点（startPoint），结束点(endPoint)，距离convexity hull最远点(farPoint)，最远点到convexity hull的距离(depth)。

 

二．OpenCV中的相关函数

void convexityDefects(InputArray contour, InputArray convexhull, OutputArrayconvexityDefects)

参数：

coutour: 输入参数，检测到的轮廓，可以调用findContours函数得到；

convexhull: 输入参数，检测到的凸包，可以调用convexHull函数得到。注意，convexHull函数可以得到vector<vector<Point>>和vector<vector<int>>两种类型结果，这里的convexhull应该为vector<vector<int>>类型，否则通不过ASSERT检查；

convexityDefects：输出参数，检测到的最终结果，应为vector<vector<Vec4i>>类型，Vec4i存储了起始点（startPoint），结束点(endPoint)，距离convexity hull最远点(farPoint)以及最远点到convexity hull的距离(depth)

 

三．代码

//http://docs.opencv.org/doc/tutorials/imgproc/shapedescriptors/hull/hull.html
//http://www.codeproject.com/Articles/782602/Beginners-guide-to-understand-Fingertips-counting

#include "opencv2/highgui/highgui.hpp"
 #include "opencv2/imgproc/imgproc.hpp"
 #include <iostream>
 #include <stdio.h>
 #include <stdlib.h>

 using namespace cv;
 using namespace std;

 Mat src; Mat src_gray;
 int thresh = 100;
 int max_thresh = 255;
 RNG rng(12345);

 /// Function header
 void thresh_callback(int, void* );

/** @function main */
int main( int argc, char** argv )
 {
   /// Load source image and convert it to gray
   src = imread( argv[1], 1 );

   /// Convert image to gray and blur it
   cvtColor( src, src_gray, CV_BGR2GRAY );
   blur( src_gray, src_gray, Size(3,3) );

   /// Create Window
   char* source_window = "Source";
   namedWindow( source_window, CV_WINDOW_AUTOSIZE );
   imshow( source_window, src );

   createTrackbar( " Threshold:", "Source", &thresh, max_thresh, thresh_callback );
   thresh_callback( 0, 0 );

   waitKey(0);
   return(0);
 }

 /** @function thresh_callback */
 void thresh_callback(int, void* )
 {
   Mat src_copy = src.clone();
   Mat threshold_output;
   vector<vector<Point> > contours;
   vector<Vec4i> hierarchy;

   /// Detect edges using Threshold
   threshold( src_gray, threshold_output, thresh, 255, THRESH_BINARY );

   /// Find contours
   findContours( threshold_output, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0, 0) );

   /// Find the convex hull object for each contour
   vector<vector<Point> >hull( contours.size() );
   // Int type hull
   vector<vector<int>> hullsI( contours.size() );
   // Convexity defects
   vector<vector<Vec4i>> defects( contours.size() );

   for( size_t i = 0; i < contours.size(); i++ )
   {  
	   convexHull( Mat(contours[i]), hull[i], false ); 
	   // find int type hull
	   convexHull( Mat(contours[i]), hullsI[i], false ); 
	   // get convexity defects
	   convexityDefects(Mat(contours[i]),hullsI[i], defects[i]);
   
   }

   /// Draw contours + hull results
   Mat drawing = Mat::zeros( threshold_output.size(), CV_8UC3 );
   for( size_t i = 0; i< contours.size(); i++ )
      {
        Scalar color = Scalar( rng.uniform(0, 255), rng.uniform(0,255), rng.uniform(0,255) );
        drawContours( drawing, contours, i, color, 1, 8, vector<Vec4i>(), 0, Point() );
        drawContours( drawing, hull, i, color, 1, 8, vector<Vec4i>(), 0, Point() );

		// draw defects
		size_t count = contours[i].size();
        std::cout<<"Count : "<<count<<std::endl;
        if( count < 300 )
            continue;

        vector<Vec4i>::iterator d =defects[i].begin();

        while( d!=defects[i].end() ) {
            Vec4i& v=(*d);
            //if(IndexOfBiggestContour == i)
			{

                int startidx=v[0]; 
                Point ptStart( contours[i][startidx] ); // point of the contour where the defect begins
                int endidx=v[1]; 
                Point ptEnd( contours[i][endidx] ); // point of the contour where the defect ends
                int faridx=v[2]; 
                Point ptFar( contours[i][faridx] );// the farthest from the convex hull point within the defect
                int depth = v[3] / 256; // distance between the farthest point and the convex hull

                if(depth > 20 && depth < 80)
                {
                line( drawing, ptStart, ptFar, CV_RGB(0,255,0), 2 );
                line( drawing, ptEnd, ptFar, CV_RGB(0,255,0), 2 );
				circle( drawing, ptStart,   4, Scalar(255,0,100), 2 );
				circle( drawing, ptEnd,   4, Scalar(255,0,100), 2 );
                circle( drawing, ptFar,   4, Scalar(100,0,255), 2 );
                }

				/*printf("start(%d,%d) end(%d,%d), far(%d,%d)\n",
					ptStart.x, ptStart.y, ptEnd.x, ptEnd.y, ptFar.x, ptFar.y);*/
            }
            d++;
        }


      }

   /// Show in a window
   namedWindow( "Hull demo", CV_WINDOW_AUTOSIZE );
   imshow( "Hull demo", drawing );
   //imwrite("convexity_defects.jpg", drawing);
 }

四．结果

 

原图

 

Convexity defects图，蓝色点是convexity defects的起始点和结束点，红色点是最远点。（为什么有的起始点和结束点中间没有最远点呢？因为只画出了depth范围在20到80之间的convexity defects的起始点、结束点和最远点）

 

五．参考

[1] Gary Bradski, Adrian Kaehler. Learning OpenCV: Computer Vision with the OpenCV Library. Page258~259.

[2] http://docs.opencv.org/doc/tutorials/imgproc/shapedescriptors/hull/hull.html

[3] http://www.codeproject.com/Articles/782602/Beginners-guide-to-understand-Fingertips-counting