opencv3/C++ FLANN特征匹配方式

更新時間：2019年12月11日 15:38:29 作者：阿卡蒂奧

今天小編就為大家分享一篇opencv3/C++ FLANN特征匹配方式，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

使用函數(shù)detectAndCompute(）檢測關鍵點并計算描述符

函數(shù)detectAndCompute(）參數(shù)說明：

void detectAndCompute( 
InputArray image, //圖像
InputArray mask, //掩模
CV_OUT std::vector<KeyPoint>& keypoints,//輸出關鍵點的集合
OutputArray descriptors,//計算描述符（descriptors[i]是為keypoints[i]的計算描述符）
bool useProvidedKeypoints=false //使用提供的關鍵點
);

match(）從查詢集中查找每個描述符的最佳匹配。

參數(shù)說明：

void match( 
InputArray queryDescriptors, //查詢描述符集
InputArray trainDescriptors, //訓練描述符集合
CV_OUT std::vector<DMatch>& matches, //匹配
InputArray mask=noArray() //指定輸入查詢和描述符的列表矩陣之間的允許匹配的掩碼
) const;

FLANN特征匹配示例：

#include<opencv2/opencv.hpp>
#include<opencv2/xfeatures2d.hpp>
using namespace cv;
using namespace cv::xfeatures2d;

//FLANN對高維數(shù)據(jù)較快
int main()
{
  Mat src1,src2;
  src1 = imread("E:/image/image/card2.jpg");
  src2 = imread("E:/image/image/cards.jpg");
  if (src1.empty() || src2.empty())
  {
    printf("can ont load images....\n");
    return -1;
  }
  imshow("image1", src1);
  imshow("image2", src2);

  int minHessian = 400;
  //選擇SURF特征
  Ptr<SURF>detector = SURF::create(minHessian);
  std::vector<KeyPoint>keypoints1;
  std::vector<KeyPoint>keypoints2;
  Mat descriptor1, descriptor2;
  //檢測關鍵點并計算描述符
  detector->detectAndCompute(src1, Mat(), keypoints1, descriptor1);
  detector->detectAndCompute(src2, Mat(), keypoints2, descriptor2);

  //基于Flann的描述符匹配器
  FlannBasedMatcher matcher;
  std::vector<DMatch>matches;
  //從查詢集中查找每個描述符的最佳匹配
  matcher.match(descriptor1, descriptor2, matches);
  double minDist = 1000;
  double maxDist = 0;
  for (int i = 0; i < descriptor1.rows; i++)
  {
    double dist = matches[i].distance;
    printf("%f \n", dist);
    if (dist > maxDist)
    {
      maxDist = dist;
    }
    if (dist < minDist)
    {
      minDist = dist;
    }

  }
  //DMatch類用于匹配關鍵點描述符的
  std::vector<DMatch>goodMatches;
  for (int i = 0; i < descriptor1.rows; i++)
  {
    double dist = matches[i].distance;
    if (dist < max(2.5*minDist, 0.02))
    {
      goodMatches.push_back(matches[i]);
    }
  }
  Mat matchesImg;
  drawMatches(src1, keypoints1, src2, keypoints2, goodMatches, matchesImg, Scalar::all(-1), Scalar::all(-1), std::vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
  imshow("output", matchesImg);

  waitKey();
  return 0;
}