【CS】尺度不变特征变换匹配算法SIFT（2）

尺度不变特征变换匹配算法SIFT（2）

e-mail:[e-mail]

SIFT算法

      在10月初，草草学习了一下SIFT（可以戳这里查看），主要是调用opencv函数库了的函数进行了实践，而并没有深入了解SIFT描述子的原理以及opencv中相关函数的用法和参数说明。本篇blog作为LZ的小笔记，记录一下opencv中相关函数的说明，对于SIFT特征的原理后续将花时间继续了解。

C++代码

环境：vs2010+opencv2.3.1+win7 ×64

     这部分代码还是使用上一篇SIFT的代码，本篇重在了解一些函数和数据结构。

#include <opencv2/opencv.hpp>  #include <istream>    using namespace std;  using namespace cv;  int main()  {      //read the two input images      Mat image1 = imread("image1.jpg");      Mat image2 = imread("image2.jpg");      //if failed      if(image1.empty()||image2.empty())      {          cout<<"error,the image is not exist"<<endl;          return -1;      }      //difine a sift detector      SiftFeatureDetector siftDetector;      //store key points      vector<KeyPoint> keypoint1,keypoint2;      //detect image with SIFT,get key points      siftDetector.detect(image1,keypoint1);      Mat outImage1;      //draw key points at the out image and show to the user      drawKeypoints(image1,keypoint1,outImage1,Scalar(255,0,0));        imshow("original_image1",image1);      imshow("sift_image1",outImage1);            Mat outImage2;            siftDetector.detect(image2,keypoint2);      drawKeypoints(image2,keypoint2,outImage2,Scalar(255,0,0));        imshow("sift_image2.jpg",outImage2);      //imwrite("sift_result2.jpg",outImage2);      //store 10 keypoints in order to watch the effect clearly      vector<KeyPoint> keypoint3,keypoint4;      for(int i=0;i<10;i++)      {          keypoint3.push_back(keypoint1[i]);          keypoint4.push_back(keypoint2[i]);      }      // difine a sift descriptor extractor      SiftDescriptorExtractor extractor;      //store the descriptor of each image      Mat descriptor1,descriptor2;      BruteForceMatcher<L2<float>> matcher;        vector<DMatch> matches;      Mat img_matches;      //compute the descriptor of each image      extractor.compute(image1,keypoint3,descriptor1);      extractor.compute(image2,keypoint4,descriptor2);      //match      matcher.match(descriptor1,descriptor2,matches);      //show the result      drawMatches(image1,keypoint3,image2,keypoint4,matches,img_matches,Scalar(255,0,0));      imshow("matches",img_matches);      //store the match_image      //imwrite("matches.jpg",img_matches);        waitKey(0);      return 0;  }  

opencv相关函数和数据结构说明

1.drawMatcher():Draws the found matches of keypoints from two images.

参考：http://docs.opencv.org/2.4/modules/features2d/doc/drawing_function_of_keypoints_and_matches.html

C++: void drawMatches(const Mat& img1, const vector<KeyPoint>& keypoints1, const Mat& img2, const  vector<KeyPoint>& keypoints2, const vector<vector<DMatch>>& matches1to2,    Mat& outImg, const Scalar& matchColor=Scalar::all(-1),  const Scalar& singlePointColor=Scalar::all(-1),   const vector<vector<char>>& matchesMask=vector<vector<char> >(), int flags=DrawMatchesFlags::DEFAULT )

• img1 – First source image.
• keypoints1 – Keypoints from the first source image.
• img2 – Second source image.
• keypoints2 – Keypoints from the second source image.
• matches1to2 – Matches from the first image to the second one, which means that keypoints1[i] has a corresponding point in keypoints2[matches[i]] .
• outImg – Output image. Its content depends on the flags value defining what is drawn in the output image. See possible flags bit values below.
• matchColor – Color of matches (lines and connected keypoints). If matchColor==Scalar::all(-1) , the color is generated randomly.
• singlePointColor – Color of single keypoints (circles), which means that keypoints do not have the matches. If singlePointColor==Scalar::all(-1) , the color is generated randomly.
• matchesMask – Mask determining which matches are drawn. If the mask is empty, all matches are drawn.
• flags – Flags setting drawing features. Possible flags bit values are defined by DrawMatchesFlags.

2.DMatch:Class for matching keypoint descriptors: query descriptor index, train descriptor index, train image index, and distance between descriptors. 

可参考：http://docs.opencv.org/master/d4/de0/classcv_1_1DMatch.html

<span style="font-family:Microsoft YaHei;">       struct DMatch       {              //三个构造函数           DMatch(): queryIdx(-1), trainIdx(-1),imgIdx(-1),distance(std::numeric_limits<float>::max()) {}           DMatch(int  _queryIdx, int  _trainIdx, float  _distance ) :                            queryIdx( _queryIdx),trainIdx( _trainIdx), imgIdx(-1),distance( _distance) {}           DMatch(int  _queryIdx, int  _trainIdx, int  _imgIdx, float  _distance ) :                   queryIdx(_queryIdx), trainIdx( _trainIdx), imgIdx( _imgIdx),distance( _distance) {}            intqueryIdx;  //此匹配对应的查询图像的特征描述子索引           inttrainIdx;   //此匹配对应的训练(模板)图像的特征描述子索引           intimgIdx;    //训练图像的索引(若有多个)           float distance;  //两个特征向量之间的欧氏距离，越小表明匹配度越高。           booloperator < (const DMatch &m) const;       };</span>

一般使用Brute-force descriptor matcher进行匹配，结果并不具有可读性（戳这里看图），那么这里请留意匹配的结果保存在了vector<DMatch>定义的动态数组matches中，这就意味着我们可以对匹配结果进行一系列操作，比如再drawMatches()函数前添加一句：matches.erase(matches.begin()+25,matches.end()); 既可以选择最新的25个匹配结果。