opencv-形态学处理

原理摘自：http://www.opencv.org.cn/opencvdoc/2.3.2/html/doc/tutorials/imgproc/opening_closing_hats/opening_closing_hats.html

开运算是通过先对图像腐蚀再膨胀实现的。

能够排除小团块物体(假设物体较背景明亮)

请看下面，左图是原图像，右图是采用开运算转换之后的结果图。 观察发现字母拐弯处的白色空间消失。

闭运算是通过先对图像膨胀再腐蚀实现的。

能够排除小型黑洞(黑色区域)。

膨胀图与腐蚀图之差

能够保留物体的边缘轮廓，如下所示:

原图像与开运算结果图之差

闭运算结果图与原图像之差

// ConsoleApplication3_6_23.cpp : Defines the entry point for the console application.
//

#include "stdafx.h"
#include<opencv2/opencv.hpp>
#include<iostream>
using namespace std;
using namespace cv;

Mat src,dst;

int pro_elem = 0;
int pro_size = 0;
int pro_operator = 0;

const int max_elem = 2;
const int max_size = 21;
const int max_operator = 4;

char* windowName = "Demo";
void Image_pro(int,void*);

int _tmain(int argc, _TCHAR* argv[])
{
	src = imread("hwl.jpg");
	if(!src.data)
		return -1;

	namedWindow(windowName,CV_WINDOW_AUTOSIZE);

	createTrackbar("Operator:\n 0:opening-1:closing-2:gradient-3:Top Hat-4:	Black Hat",
		windowName,&pro_operator,max_operator,Image_pro);

	createTrackbar("Element:\n 0:Rect-1:Cross-2:Ellipse",
		windowName,&pro_elem,max_elem,Image_pro);

	createTrackbar("Kernel size:\n 2n+1",
		windowName,&pro_size,max_size,Image_pro);
	
	Image_pro(0,0);
	waitKey(0);
	return 0;
}

void Image_pro(int,void*)
{
	int operation = pro_operator + 2;
	Mat  element = getStructuringElement(pro_elem,Size(2*pro_size+1,2*pro_size+1),
		Point(pro_size,pro_size));
	morphologyEx(src,dst,operation,element);
	imshow(windowName,dst);
}