from：  http://www.xuebuyuan.com/582331.html

简单的通过特征点分类的方法：                                                                      

一、train

1.提取+/- sample的feature，每幅图提取出的sift特征个数不定（假设每个feature有128维）

2.利用聚类方法（e.g K-means）将不定数量的feature聚类为固定数量的(比如10个)words即BOW（bag of word）

（本篇主要完成以上的工作！）

3.normalize，并作这10个类的直方图e.g [0.1，0.2，0.7，0...0];

4.将each image的这10个word作为feature_instance 和 (手工标记的) label（+/-）进入SVM训练

 

二、predict

1. 提取test_img的feature（如137个）

2. 分别求each feature与10个类的距离(e.g. 128维欧氏距离)，确定该feature属于哪个类

3. normalize，并作这10个类的直方图e.g [0，0.2，0.2，0.6，0...0];

4. 应用SVM_predict进行结果预测

 

 

通过OpenCV实现feature聚类 BOW                                                             

首先在此介绍一下OpenCV的特征描述符与BOW的通用函数。

主要的通用接口有：

 

1.特征点提取

Ptr<FeatureDetector> FeatureDetector::create(const string& detectorType)

Ptr
    
      FeatureDetector::create(const string& detectorType)// 	"FAST" – FastFeatureDetector // 	"STAR" – StarFeatureDetector // 	"SIFT" – SIFT (nonfree module)//必须使用 initModule_nonfree()初始化// 	"SURF" – SURF (nonfree module)//同上; // 	"ORB" – ORB // 	"MSER" – MSER // 	"GFTT" – GoodFeaturesToTrackDetector // 	"HARRIS" – GoodFeaturesToTrackDetector with Harris detector enabled // 	"Dense" – DenseFeatureDetector // 	"SimpleBlob" – SimpleBlobDetector
    

 

根据以上接口，测试不同的特征点：

对同一幅图像进行水平翻转前后的两幅图像检测特征点检测结果，

检测到的特征点的坐标类型为：pt: int / float（与keyPoint的性质有关）

数量分别为num1, num2,

 

 "FAST" – FastFeatureDetector           pt:int (num1:615  num2:618)

 "STAR" – StarFeatureDetector           pt:int (num1:43   num2:42 )

 "SIFT" – SIFT (nonfree module)          pt:float(num1:155  num2:135)            //必须使用 initModule_nonfree()初始化

 "SURF" – SURF (nonfree module)     pt:float(num1:344  num2:342)           

//同上; 

 "ORB" – ORB                                        pt:float(num1:496  num2:497)

 "MSER" – MSER                                 pt:float(num1:51   num2:45 )

 "GFTT" – GoodFeaturesToTrackDetector        pt:int (num1:744  num2:771)

 "HARRIS" – GoodFeaturesToTrackDetector with Harris detector enabled         pt:float(num1:162  num2:160)

 "Dense" – DenseFeatureDetector          pt:int (num1:3350 num2:3350)

 

2.特征描述符提取

Ptr<DescriptorExtractor> DescriptorExtractor::create(const string& descriptorExtractorType)

//  Ptr
    
      DescriptorExtractor::create(const string& descriptorExtractorType)	// 	"SIFT" – SIFT // 	"SURF" – SURF // 	"ORB" – ORB // 	"BRIEF" – BriefDescriptorExtractor
    

 

3.描述符匹配

Ptr<DescriptorMatcher> descriptorMatcher = DescriptorMatcher::create(const string& descriptorMatcherType)

// 	descriptorMatcherType – Descriptor matcher type. //	Now the following matcher types are supported: // 		BruteForce (it uses L2 ) // 		BruteForce-L1 // 		BruteForce-Hamming // 		BruteForce-Hamming(2) // 		FlannBased 	Ptr
    
      descriptorMatcher = DescriptorMatcher::create( "BruteForce" );
    

 

4.class BOWTrainer

class BOWKmeansTrainer::public BOWTrainer:Kmeans训练

BOWKMeansTrainer ::BOWKmeansTrainer(int clusterCount, const TermCriteria& termcrit=TermCriteria(), int attempts=3, int flags=KMEANS_PP_CENTERS)

parameter same as 

 

实现：                                                                                                                    

1.画特征点。

2.特征点聚类，每一种颜色代表一个类别。

 

#include "opencv2/highgui/highgui.hpp"#include "opencv2/calib3d/calib3d.hpp"#include "opencv2/imgproc/imgproc.hpp"#include "opencv2/features2d/features2d.hpp"#include "opencv2/nonfree/nonfree.hpp"#include 
    
     using namespace cv;using namespace std;#define ClusterNum 10void DrawAndMatchKeypoints(const Mat& Img1,const Mat& Img2,const vector
     
      & Keypoints1,	const vector
      
       & Keypoints2,const Mat& Descriptors1,const Mat& Descriptors2){	Mat keyP1,keyP2;	drawKeypoints(Img1,Keypoints1,keyP1,Scalar::all(-1),0);	drawKeypoints(Img2,Keypoints2,keyP2,Scalar::all(-1),0);	putText(keyP1, "drawKeyPoints", cvPoint(10,30), FONT_HERSHEY_SIMPLEX, 1 ,Scalar :: all(-1));	putText(keyP2, "drawKeyPoints", cvPoint(10,30), FONT_HERSHEY_SIMPLEX, 1 ,Scalar :: all(-1));	imshow("img1 keyPoints",keyP1);	imshow("img2 keyPoints",keyP2);	Ptr
       
         descriptorMatcher = DescriptorMatcher::create( "BruteForce" );	vector
        
          matches;	descriptorMatcher->match( Descriptors1, Descriptors2, matches );	Mat show;	drawMatches(Img1,Keypoints1,Img2,Keypoints2,matches,show,Scalar::all(-1),CV_RGB(255,255,255),Mat(),4);	putText(show, "drawMatchKeyPoints", cvPoint(10,30), FONT_HERSHEY_SIMPLEX, 1 ,Scalar :: all(-1));  	imshow("match",show);}//测试OpenCV：class BOWTrainervoid BOWKeams(const Mat& img, const vector
         
          & Keypoints, const Mat& Descriptors, Mat& centers){ //BOW的kmeans算法聚类; BOWKMeansTrainer bowK(ClusterNum, cvTermCriteria (CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 10, 0.1),3,2); centers = bowK.cluster(Descriptors); cout<
          
           <<"< cluster num: "<
           
            <<" >"<
            
              descriptorMatcher = DescriptorMatcher::create( "BruteForce" ); vector
             
               matches; descriptorMatcher->match(Descriptors,centers,matches);//const Mat& queryDescriptors, const Mat& trainDescriptors第一个参数是待分类节点，第二个参数是聚类中心; Mat demoCluster; img.copyTo(demoCluster); //为每一类keyPoint定义一种颜色 Scalar color[]={CV_RGB(255,255,255), CV_RGB(255,0,0),CV_RGB(0,255,0),CV_RGB(0,0,255), CV_RGB(255,255,0),CV_RGB(255,0,255),CV_RGB(0,255,255), CV_RGB(123,123,0),CV_RGB(0,123,123),CV_RGB(123,0,123)}; for (vector
              
               ::iterator iter=matches.begin();iter!=matches.end();iter++) { cout<<"< descriptorsIdx:"<
               
                queryIdx<<" centersIdx:"<
                
                 trainIdx <<" distincs:"<
                 
                  distance<<" >"<
                  
                   queryIdx].pt; circle(demoCluster,center,2,color[iter->trainIdx],-1); } putText(demoCluster, "KeyPoints Clustering: 一种颜色代表一种类型", cvPoint(10,30), FONT_HERSHEY_SIMPLEX, 1 ,Scalar :: all(-1)); imshow("KeyPoints Clusrtering",demoCluster); }int main(){ cv::initModule_nonfree();//使用SIFT/SURF create之前，必须先initModule_
                   
                    (); cout << "< Creating detector, descriptor extractor and descriptor matcher ..."; Ptr
                    
                      detector = FeatureDetector::create( "SIFT" ); Ptr
                     
                       descriptorExtractor = DescriptorExtractor::create( "SIFT" ); Ptr
                      
                        descriptorMatcher = DescriptorMatcher::create( "BruteForce" ); cout << ">" << endl; if( detector.empty() || descriptorExtractor.empty() ) { cout << "Can not create detector or descriptor exstractor or descriptor matcher of given types" << endl; return -1; } cout << endl << "< Reading images..." << endl; Mat img1 = imread("D:/demo0.jpg"); Mat img2 = imread("D:/demo1.jpg"); cout<
                       
                        <<">"<
                        
                          keypoints1,keypoints2; detector->detect( img1, keypoints1 ); detector->detect( img2, keypoints2 ); cout <<"img1:"<< keypoints1.size() << " points img2:" <
                         
                          << " points" << endl << ">" << endl; //compute descriptors for keypoints; cout << "< Computing descriptors for keypoints from images..." << endl; Mat descriptors1,descriptors2; descriptorExtractor->compute( img1, keypoints1, descriptors1 ); descriptorExtractor->compute( img2, keypoints2, descriptors2 ); cout<
                          
                           <<"< Descriptoers Size: "<
                           
                            <<" >"<
                            
                             " << endl; //Draw And Match img1,img2 keypoints //匹配的过程是对特征点的descriptors进行match; DrawAndMatchKeypoints(img1,img2,keypoints1,keypoints2,descriptors1,descriptors2); Mat center; //对img1提取特征点，并聚类 //测试OpenCV：class BOWTrainer BOWKeams(img1,keypoints1,descriptors1,center); waitKey();}
                            
                           
                          
                         
                        
                       
                      
                     
                    
                   
                  
                 
                
               
              
             
            
           
          
         
        
       
      
     
    

 

 

通过Qt实现DrawKeypoints：

void Qt_test1::on_DrawKeypoints_clicked(){	//initModule_nonfree();	Ptr
    
      detector = FeatureDetector::create( "FAST" );	vector
     
       keypoints;	detector->detect( src, keypoints );	Mat DrawKeyP;	drawKeypoints(src,keypoints,DrawKeyP,Scalar::all(-1),0);	putText(DrawKeyP, "drawKeyPoints", cvPoint(10,30), 		FONT_HERSHEY_SIMPLEX, 0.5 ,Scalar :: all(255));	cvtColor(DrawKeyP, image, CV_RGB2RGBA);	QImage img = QImage((const unsigned char*)(image.data), 		image.cols, image.rows, QImage::Format_RGB32);	QLabel *label = new QLabel(this);	label->move(50, 50);//图像在窗口中所处的位置;	label->setPixmap(QPixmap::fromImage(img));	label->resize(label->pixmap()->size());		label->show();}
     
    

由于initModule_nonfree()总是出错，无法对SIFT与SURF特征点提取，

而且无法实现聚类因为运行/BOW的kmeans算法聚类：BOWKMeansTrainer bowK(ClusterNum, cvTermCriteria (CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 10, 0.1),3,2);总是出错，不知道咋解决~~~~~(>_<)~~~~ 需要继续学习