opencv模板匹配

1.源码实现

#include <cstdio>
#include <iostream>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>

using namespace std;
using namespace cv;

void MatchingMethod(Mat &img, Mat &temp, Mat &result, const int match_method)
{
    //将被显示的原图像
    Mat img_display;

    img.copyTo(img_display);

    //创建输出结果的矩阵
    int result_cols = img.cols - temp.cols + 1;
    int result_rows = img.rows - temp.rows + 1;

    //进行匹配和标准化
    matchTemplate(img, temp, result, match_method);
    normalize(result, result, 0, 1, NORM_MINMAX, -1, Mat());

    //通过函数 minMaxLoc 定位最匹配的位置
    Point minLoc, maxLoc, matchLoc;
    double minVal, maxVal;

    minMaxLoc(result, &minVal, &maxVal, &minLoc, &maxLoc, Mat());

    //对于方法 SQDIFF 和 SQDIFF_NORMED, 越小的数值代表更高的匹配结果. 而对于其他方法, 数值越大匹配越好
    if(match_method  == CV_TM_SQDIFF || match_method == CV_TM_SQDIFF_NORMED)
    {
        matchLoc = minLoc;
    }
    else
    {
        matchLoc = maxLoc;
    }

    //看看最终结果
    rectangle(img_display, matchLoc, Point(matchLoc.x + temp.cols , matchLoc.y + temp.rows), Scalar(0, 0, 255), 2, 8, 0);
    rectangle(result, matchLoc, Point(matchLoc.x + temp.cols , matchLoc.y + temp.rows), Scalar::all(0), 2, 8, 0);

    //cout << img_display << endl;

    imwrite("matchresult.jpg", img_display);
}

int main(int argc, char **argv)
{
    if(argc <= 2)
    {
        return -1;
    }

    //载入原图像和模板块
    Mat img = imread(argv[1], 1);
    Mat temp = imread(argv[2], 1);
    Mat result;

    //设置方法Method: 0: SQDIFF 1: SQDIFF NORMED 2: TM CCORR 3: TM CCORR NORMED 4: TM COEFF 5: TM COEFF NORMED
    int method = 1;

    MatchingMethod(img, temp, result, method);

    return 0;
}

2.编译源码

$ g++ -o test test.cpp -std=c++11 -I/usr/local/include/opencv4 -L/usr/local/lib -lopencv_core -lopencv_highgui -lopencv_imgproc -lopencv_ml -Wl,-rpath=/usr/local/lib

3.运行及其结果

3.jpg
6.jpg
matchresult.jpg