opencv学习-pca人脸识别

本文转载自http://www.cnblogs.com/zcftech/archive/2013/04/17/3026902.html

上一节我们已经将图片进行降维处理，这样做的目的就是要在保持对象间差异的同时降低处理数据量。除了PCA外，LDA也是一种比较简单实用的降维方法，大家可以对比两种降维方法；基于PCA降维后的数据，我们接着要做的是用训练数据将测试数据表示出来

接着通过以下的误差判别式来找到M近邻（误差值越小说明该训练样本跟测试样本的相似度越大）

       

以上就完成了两步法中的第一步，第二步中用M近邻样本将测试样本再次标出（实际上这里的本质还是稀疏表示的方法，但是改进之处是单纯的稀疏法中稀疏项不确定，两步法中通过第一步的误差筛选确定了贡献度较大的训练样本）

在M近邻中包含多个类的训练样本，我们要将每个类的训练样本累加起来，分别同测试样本做误差对比，将测试样本判定给误差最下的类

       

OK，主要思想介绍了，下面就看代码实

/************************************************************************//* ZhaoChaofeng*/ 2013.4.16/************************************************************************/#include <opencv2/core/core.hpp>#include <opencv2/highgui/highgui.hpp>#include <fstream>#include <sstream>#include <iostream>#include <string>using namespace cv;using namespace std;const double u=0.01f;const double v=0.01f;//the global parameterconst int MNeighbor=40;//the M nearest neighbors// Number of components to keep for the PCAconst int num_components = 100;//the M neighbor matsvector<Mat> MneighborMat;//the class index of M neighbor matsvector<int> MneighborIndex;//the number of object which used to trainingconst int Training_ObjectNum=40;//the number of image that each object usedconst int Training_ImageNum=7;//the number of object used to testingconst int Test_ObjectNum=40;//the image numberconst int Test_ImageNum=3;// Normalizes a given image into a value range between 0 and 255.Mat norm_0_255(const Mat& src) {    // Create and return normalized image:    Mat dst;    switch(src.channels()) {    case 1:        cv::normalize(src, dst, 0, 255, NORM_MINMAX, CV_8UC1);        break;    case 3:        cv::normalize(src, dst, 0, 255, NORM_MINMAX, CV_8UC3);        break;    default:        src.copyTo(dst);        break;    }    return dst;}// Converts the images given in src into a row matrix.Mat asRowMatrix(const vector<Mat>& src, int rtype, double alpha = 1, double beta = 0) {    // Number of samples:    size_t n = src.size();    // Return empty matrix if no matrices given:    if(n == 0)        return Mat();    // dimensionality of (reshaped) samples    size_t d = src[0].total();    // Create resulting data matrix:    Mat data(n, d, rtype);    // Now copy data:    for(int i = 0; i < n; i++) {        //        if(src[i].empty()) {            string error_message = format("Image number %d was empty, please check your input data.", i);            CV_Error(CV_StsBadArg, error_message);        }        // Make sure data can be reshaped, throw a meaningful exception if not!        if(src[i].total() != d) {            string error_message = format("Wrong number of elements in matrix #%d! Expected %d was %d.", i, d, src[i].total());            CV_Error(CV_StsBadArg, error_message);        }        // Get a hold of the current row:        Mat xi = data.row(i);        // Make reshape happy by cloning for non-continuous matrices:        if(src[i].isContinuous()) {            src[i].reshape(1, 1).convertTo(xi, rtype, alpha, beta);        } else {            src[i].clone().reshape(1, 1).convertTo(xi, rtype, alpha, beta);        }    }    return data;}//convert int to stringstring Int_String(int index){    stringstream ss;    ss<<index;    return ss.str();}////show the element of mat(used to test code)//void showMat(Mat RainMat)//{//    for (int i=0;i<RainMat.rows;i++)//    {//        for (int j=0;j<RainMat.cols;j++)//        {//            cout<<RainMat.at<float>(i,j)<<"  ";//        }//        cout<<endl;//    }//}//////show the element of vector//void showVector(vector<int> index)//{//    for (int i=0;i<index.size();i++)//    {//        cout<<index[i]<<endl;//    }//}////void showMatVector(vector<Mat> neighbor)//{//    for (int e=0;e<neighbor.size();e++)//    {//        showMat(neighbor[e]);//    }//}//Training functionvoid Trainging(){    // Holds some training images:    vector<Mat> db;    // This is the path to where I stored the images, yours is different!    for (int i=1;i<=Training_ObjectNum;i++)    {        for (int j=1;j<=Training_ImageNum;j++)        {            string filename="s"+Int_String(i)+"/"+Int_String(j)+".pgm";            db.push_back(imread(filename,IMREAD_GRAYSCALE));        }    }    // Build a matrix with the observations in row:    Mat data = asRowMatrix(db, CV_32FC1);    // Perform a PCA:    PCA pca(data, Mat(), CV_PCA_DATA_AS_ROW, num_components);    // And copy the PCA results:    Mat mean = pca.mean.clone();    Mat eigenvalues = pca.eigenvalues.clone();    Mat eigenvectors = pca.eigenvectors.clone();    // The mean face:    //imshow("avg", norm_0_255(mean.reshape(1, db[0].rows)));    // The first three eigenfaces:    //imshow("pc1", norm_0_255(pca.eigenvectors.row(0)).reshape(1, db[0].rows));    //imshow("pc2", norm_0_255(pca.eigenvectors.row(1)).reshape(1, db[0].rows));    //imshow("pc3", norm_0_255(pca.eigenvectors.row(2)).reshape(1, db[0].rows));    ////get and save the training image information which decreased on dimensionality    Mat mat_trans_eigen;    Mat temp_data=data.clone();    Mat temp_eigenvector=pca.eigenvectors.clone();    gemm(temp_data,temp_eigenvector,1,NULL,0,mat_trans_eigen,CV_GEMM_B_T);    //save the eigenvectors    FileStorage fs(".\\eigenvector.xml", FileStorage::WRITE);    fs<<"eigenvector"<<eigenvectors;    fs<<"TrainingSamples"<<mat_trans_eigen;    fs.release();}//Line combination of test sample used by training samples //parameter:y stand for the test sample column vector;//x stand for the training samples matrixMat LineCombination(Mat y,Mat x){    //the number of training samples    size_t col=x.cols;    //the result mat     Mat result=cvCreateMat(col,1,CV_32FC1);    //the transposition of x and also work as a temp matrix    Mat trans_x_mat=cvCreateMat(col,col,CV_32FC1);    //construct the identity matrix    Mat I=Mat::ones(col,col,CV_32FC1);    //solve the Y=XA    //result=x.inv(DECOMP_SVD);        //result*=y;    Mat temp=(x.t()*x+u*I);        Mat temp_one=temp.inv(DECOMP_SVD);    Mat temp_two=x.t()*y;    result=temp_one*temp_two;    return result;}//Error test//parameter:y stand for the test sample column vector;//x stand for the training samples matrix//coeff stand for the coefficient of training samples void  ErrorTest(Mat y,Mat x,Mat coeff){    //the array store the coefficient    map<double,int> Efficient;    //compute the error    for (int i=0;i<x.cols;i++)    {        Mat temp=x.col(i);        double coefficient=coeff.at<float>(i,0);        temp=coefficient*temp;        double e=norm((y-temp),NORM_L2);        Efficient[e]=i;//insert a new element    }    //select the minimum w col as the w nearest neighbors    map<double,int>::const_iterator map_it=Efficient.begin();    int num=0;    //the map could sorted by the key one    while (map_it!=Efficient.end() && num<MNeighbor)    {        MneighborMat.push_back(x.col(map_it->second));        MneighborIndex.push_back(map_it->second);        ++map_it;        ++num;    }    //return MneighborMat;}//error test of two step//parameter:MneighborMat store the class information of M nearest neighbor samplesint ErrorTest_Two(Mat y,Mat x,Mat coeff){    int result;    bool flag=true;    double minimumerror;    //    map<int,vector<Mat>> ErrorResult;    //count the class of M neighbor    for (int i=0;i<x.cols;i++)    {        //compare        //Mat temp=x.col(i)==MneighborMat[i];          //showMat(temp);        //if (temp.at<float>(0,0)==255)        //{            int classinf=MneighborIndex[i];            double coefficient=coeff.at<float>(i,0);            Mat temp=x.col(i);            temp=coefficient*temp;            ErrorResult[classinf/Training_ImageNum].push_back(temp);        //}            }    //    map<int,vector<Mat>>::const_iterator map_it=ErrorResult.begin();    while(map_it!=ErrorResult.end())    {        vector<Mat> temp_mat=map_it->second;        int num=temp_mat.size();        Mat temp_one;        temp_one=Mat::zeros(temp_mat[0].rows,temp_mat[0].cols,CV_32FC1);        while (num>0)        {            temp_one+=temp_mat[num-1];            num--;        }        double e=norm((y-temp_one),NORM_L2);        if (flag)        {            minimumerror=e;            result=map_it->first+1;            flag=false;        }        if (e<minimumerror)        {            minimumerror=e;            result=map_it->first+1;        }        ++map_it;    }    return result;}//testing function//parameter:y stand for the test sample column vector;//x stand for the training samples matrixint testing(Mat x,Mat y){    // the class that test sample belongs to    int classNum;    //the first step: get the M nearest neighbors    Mat coffecient=LineCombination(y.t(),x.t());    //cout<<"the first step coffecient"<<endl;    //showMat(coffecient);    //map<Mat,int> MneighborMat=ErrorTest(y,x,coffecient);    ErrorTest(y.t(),x.t(),coffecient);    //cout<<"the M neighbor index"<<endl;    //showVector(MneighborIndex);    //cout<<"the M neighbor mats"<<endl;    //showMatVector(MneighborMat);    //the second step:    //construct the W nearest neighbors mat    int row=x.cols;//should be careful     Mat temp(row,MNeighbor,CV_32FC1);    for (int i=0;i<MneighborMat.size();i++)    {        Mat temp_x=temp.col(i);        if (MneighborMat[i].isContinuous())        {            MneighborMat[i].convertTo(temp_x,CV_32FC1,1,0);        }        else        {            MneighborMat[i].clone().convertTo(temp_x,CV_32FC1,1,0);        }    }    //cout<<"the second step mat"<<endl;    //showMat(temp);    Mat coffecient_two=LineCombination(y.t(),temp);    //cout<<"the second step coffecient"<<endl;    //showMat(coffecient_two);    classNum=ErrorTest_Two(y.t(),temp,coffecient_two);    return classNum;}int main(int argc, const char *argv[]) {    //the number which test true    int TrueNum=0;    //the Total sample which be tested    int TotalNum=Test_ObjectNum*Test_ImageNum;    //if there is the eigenvector.xml, it means we have got the training data and go to the testing stage directly;    FileStorage fs(".\\eigenvector.xml", FileStorage::READ);    if (fs.isOpened())    {        //if the eigenvector.xml file exist,read the mat data        Mat mat_eigenvector;        fs["eigenvector"] >> mat_eigenvector;            Mat mat_Training;        fs["TrainingSamples"]>>mat_Training;        for (int i=1;i<=Test_ObjectNum;i++)        {            int ClassTestNum=0;            for (int j=Training_ImageNum+1;j<=Training_ImageNum+Test_ImageNum;j++)            {                string filename="s"+Int_String(i)+"/"+Int_String(j)+".pgm";                Mat TestSample=imread(filename,IMREAD_GRAYSCALE);                Mat TestSample_Row;                TestSample.reshape(1,1).convertTo(TestSample_Row,CV_32FC1,1,0);//convert to row mat                Mat De_deminsion_test;                gemm(TestSample_Row,mat_eigenvector,1,NULL,0,De_deminsion_test,CV_GEMM_B_T);// get the test sample which decrease the dimensionality                //cout<<"the test sample"<<endl;                //showMat(De_deminsion_test.t());                //cout<<"the training samples"<<endl;                //showMat(mat_Training);                int result=testing(mat_Training,De_deminsion_test);                //cout<<"the result is"<<result<<endl;                if (result==i)                {                    TrueNum++;                    ClassTestNum++;                }                MneighborIndex.clear();                MneighborMat.clear();//及时清除空间            }            cout<<"第"<<Int_String(i)<<"类测试正确的图片数:  "<<Int_String(ClassTestNum)<<endl;        }        fs.release();    }    else    {        Trainging();    }    // Show the images:    waitKey(0);    // Success!    return 0;}

在以上的实现中，有些opencv的实现需要特别注意一下：

（1）坑爹的Mat类型，它虽然可以方便的让我们实现图像数据的矩阵化，并给出了一系列的操作方法，但是，在调试中，它却不能像一般变量一样，让我们直观的看到；我用一个比较笨的方法：自己写一个方法，在调试中调用，呈现关键矩阵的数据

（2）另外一个就是将训练数据做一个保存，用到了opencv中的FileStorage类；有关对中间数据的存储通常会用到.xml或者.yml文件，以下对其做个简单介绍

  新版本的OpenCV的C++接口中，imwrite()和imread()只能保存整数数据，且需要以图像格式。当需要保存浮点数据或者XML/YML文件时，之前的C语言接口cvSave()函数已经在C++接口中被删除，代替它的是    FileStorage类。这个类非常的方便，封装了很多数据结构的细节，编程的时候可以根据统一的接口对数据结构进行保存。

    1. FileStorage类写XML/YML文件

         •   新建一个FileStorage对象，以FileStorage::WRITE的方式打开一个文件。

         •   使用 << 操作对该文件进行操作。

         •   释放该对象，对文件进行关闭。

        例子如下：

FileStorage fs("test.yml", FileStorage::WRITE);    fs << "frameCount" << 5;    time_t rawtime; time(&rawtime);    fs << "calibrationDate" << asctime(localtime(&rawtime));    Mat cameraMatrix = (Mat_<double>(3,3) << 1000, 0, 320, 0, 1000, 240, 0, 0, 1); //又一种Mat初始化方式    Mat distCoeffs = (Mat_<double>(5,1) << 0.1, 0.01, -0.001, 0, 0);    fs << "cameraMatrix" << cameraMatrix << "distCoeffs" << distCoeffs;        //features为一个大小为3的向量,其中每个元素由随机数x,y和大小为8的uchar数组组成    fs << "features" << "[";    for( int i = 0; i < 3; i++ )    {        int x = rand() % 640;        int y = rand() % 480;        uchar lbp = rand() % 256;        fs << "{:" << "x" << x << "y" << y << "lbp" << "[:";        for( int j = 0; j < 8; j++ )            fs << ((lbp >> j) & 1);        fs << "]" << "}";    }    fs << "]";    fs.release();

2. FileStorage类读XML/YML文件

       FileStorage对存储内容在内存中是以层次的节点组成的，每个节点类型为FileNode，FileNode可以使单个的数值、数组或者一系列FileNode的集合。FileNode又可以看做是一个容器，使用iterator接口可以对该节点内更小单位的内容进行访问，例如访问到上面存储的文件中"features"的内容。步骤与写文件类似：

         •   新建FileStorage对象，以FileStorage::READ 方式打开一个已经存在的文件

         •   使用FileStorage::operator []()函数对文件进行读取，或者使用FileNode和FileNodeIterator

         •   使用FileStorage::release()对文件进行关闭

         例子如下：

FileStorage fs("test.yml", FileStorage::READ);    //方式一: []操作符    int frameCount = (int)fs["frameCount"];        //方式二: FileNode::operator >>()    string date;    fs["calibrationDate"] >> date;        Mat cameraMatrix2, distCoeffs2;    fs["cameraMatrix"] >> cameraMatrix2;    fs["distCoeffs"] >> distCoeffs2;        //注意FileNodeIterator的使用,似乎只能用一维数组去读取里面所有的数据    FileNode features = fs["features"];    FileNodeIterator it = features.begin(), it_end = features.end();    int idx = 0;    std::vector<uchar> lbpval;    for( ; it != it_end; ++it, idx++ )    {        cout << "feature #" << idx << ": ";        cout << "x=" << (int)(*it)["x"] << ", y=" << (int)(*it)["y"] << ", lbp: (";        (*it)["lbp"] >> lbpval;  //直接读出一维向量        for( int i = 0; i < (int)lbpval.size(); i++ )            cout << " " << (int)lbpval[i];        cout << ")" << endl;    }    fs.release();

另外，注意在新建FileStorage对象之后，并以READ或WRITE模式打开文件之后，可以用FileStorage::isOpened()查看文件状态，判断是否成功打开了文件。

有关FileStorage类的相关内容引用自：http://www.cnblogs.com/summerRQ/articles/2524560.html