【opencv学习之四十一】SIFT和SUFT算法

最新推荐文章于 2025-06-03 23:00:44 发布

原创最新推荐文章于 2025-06-03 23:00:44 发布 · 1w 阅读

46 ·

CC 4.0 BY-SA版权

opencv 专栏收录该内容

47 篇文章

订阅专栏

本文通过实例演示了SIFT和SURF两种图像特征提取算法的应用过程，包括关键点检测、描述符计算及匹配，并提供了筛选匹配结果的方法。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

SIFT和SUFT算法是有相关专利的，所以在opencv中属于"nonfree"里的，在opencv2.x.x版本可能还有保留，但是在opencv3.x.x后就没有了，需要单独下载opencv_contrib库，然后自己Cmake;

相关算法的详解这里不做过多解释了，推举两个大神博客：

1.小魏的修行的博客：http://blog.youkuaiyun.com/xiaowei_cqu/article/details/8069548；

2.赵春江的源码详细分析：http://blog.youkuaiyun.com/zhaocj/article/details/42124473；

3.详细分析算法原理：http://blog.youkuaiyun.com/zddblog/article/details/7521424；

大家可以在网上再看看，相关解释等很多；

下面贴几个简单实例：

sift实例：

void imgSIFT()//SIFT算法
{
    //sift算法不是开源的所以很多内容用起来很不方便
    //Create SIFT class pointer
    Ptr<Feature2D> f2d = xfeatures2d::SIFT::create();
    //1、读入图片
    Mat img_1 = imread("D:/ImageTest/source.png");//模板图片
    Mat img_2 = imread("D:/ImageTest/222.JPG");//检测图片
    //2、声明检测点；Detect the keypoints
    vector<KeyPoint> keypoints_1, keypoints_2;
    f2d->detect(img_1, keypoints_1);
    f2d->detect(img_2, keypoints_2);
    //3、计算描述符(特征向量)；Calculate descriptors (feature vectors)
    Mat descriptors_1, descriptors_2;
    f2d->compute(img_1, keypoints_1, descriptors_1);
    f2d->compute(img_2, keypoints_2, descriptors_2);
    //4、使用BFMatcher匹配描述符向量；Matching descriptor vector using BFMatcher
    BFMatcher matcher;
    vector<DMatch> matches;
    matcher.match(descriptors_1, descriptors_2, matches);
    //5、绘制匹配出的关键点
    Mat img_matches;
    drawMatches(img_1, keypoints_1, img_2, keypoints_2, matches, img_matches);
    imshow("match",img_matches);
    //6、匹配结果筛选
    nth_element(matches.begin(), matches.begin()+30, matches.end());   //提取出前最佳匹配结果
    matches.erase(matches.begin()+30, matches.end());    //剔除掉其余的匹配结果
    Mat img_matches2;
    drawMatches(img_1, keypoints_1, img_2, keypoints_2, matches, img_matches2);
    imshow("match2",img_matches2);
    waitKey(0);
}

效果，未过滤：

过滤后：

SURF算法:

void imgSURF()//SURF算法
{
    //1、加载图片
    Mat img_1 = imread( "D:/ImageTest/source.png", IMREAD_GRAYSCALE );//模板图片
    Mat img_2 = imread("D:/ImageTest/222.JPG", IMREAD_GRAYSCALE );//被查找图片
    //2、使用SURF检测器检测关键点，计算描述符；Detect the keypoints using SURF Detector, compute the descriptors
    int minHessian = 400;
    Ptr<SURF> detector = SURF::create();
    detector->setHessianThreshold(minHessian);
    std::vector<KeyPoint> keypoints_1, keypoints_2;
    Mat descriptors_1, descriptors_2;
    detector->detectAndCompute( img_1, Mat(), keypoints_1, descriptors_1 );
    detector->detectAndCompute( img_2, Mat(), keypoints_2, descriptors_2 );
    //3、匹配描述符向量与一个蛮力匹配；Matching descriptor vectors with a brute force matcher
    BFMatcher matcher(NORM_L2);
    std::vector< DMatch > matches;
    matcher.match( descriptors_1, descriptors_2, matches );
    //4、绘制匹配结果；Draw matches
    Mat img_matches;
    drawMatches( img_1, keypoints_1, img_2, keypoints_2, matches, img_matches );
    //5、显示检测到匹配； Show detected matches
    imshow("SURF_Matches", img_matches );
    //6、匹配结果筛选
    nth_element(matches.begin(), matches.begin()+50, matches.end());   //提取出前最佳匹配结果
    matches.erase(matches.begin()+50, matches.end());    //剔除掉其余的匹配结果
    Mat img_matches2;
    drawMatches(img_1, keypoints_1, img_2, keypoints_2, matches, img_matches2);
    imshow("SURF_Matches2",img_matches2);
    waitKey(0);
}

效果：

SURF算法计算匹配（opencv文档实例），并输出点信息：

void imgSURF2()//SURF算法2
{
      Mat img_1 = imread( "D:/ImageTest/source.png", IMREAD_GRAYSCALE );
      Mat img_2 = imread("D:/ImageTest/222.JPG", IMREAD_GRAYSCALE );
      if( !img_1.data || !img_2.data )
      { std::cout<< " --(!) Error reading images " << std::endl; }
      //-- Step 1: Detect the keypoints using SURF Detector, compute the descriptors
      int minHessian = 400;
      Ptr<SURF> detector = SURF::create();
      detector->setHessianThreshold(minHessian);
      std::vector<KeyPoint> keypoints_1, keypoints_2;
      Mat descriptors_1, descriptors_2;
      detector->detectAndCompute( img_1, Mat(), keypoints_1, descriptors_1 );
      detector->detectAndCompute( img_2, Mat(), keypoints_2, descriptors_2 );
      //-- Step 2: Matching descriptor vectors using FLANN matcher
      FlannBasedMatcher matcher;
      std::vector< DMatch > matches;
      matcher.match( descriptors_1, descriptors_2, matches );
      double max_dist = 0; double min_dist = 100;
      //-- Quick calculation of max and min distances between keypoints
      for( int i = 0; i < descriptors_1.rows; i++ )
      { double dist = matches[i].distance;
        if( dist < min_dist ) min_dist = dist;
        if( dist > max_dist ) max_dist = dist;
      }
      printf("-- Max dist : %f \n", max_dist );
      printf("-- Min dist : %f \n", min_dist );
      //-- Draw only "good" matches (i.e. whose distance is less than 2*min_dist,
      //-- or a small arbitary value ( 0.02 ) in the event that min_dist is very
      //-- small)
      //-- PS.- radiusMatch can also be used here.
      std::vector< DMatch > good_matches;
      for( int i = 0; i < descriptors_1.rows; i++ )
      { if( matches[i].distance <= max(2*min_dist, 0.02) )
        { good_matches.push_back( matches[i]); }
      }
      //-- Draw only "good" matches
      Mat img_matches;
      drawMatches( img_1, keypoints_1, img_2, keypoints_2,
                   good_matches, img_matches, Scalar::all(-1), Scalar::all(-1),
                   vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS );
      //-- Show detected matches
      imshow( "Good Matches", img_matches );
      for( int i = 0; i < (int)good_matches.size(); i++ )
      { printf( "-- Good Match [%d] Keypoint 1: %d  -- Keypoint 2: %d  \n", i, good_matches[i].queryIdx, good_matches[i].trainIdx ); }

      cout<<"key:"<<keypoints_1[0].pt.x<<endl;
      waitKey(0);
}

效果：