opencv 人脸识别 （二）训练和识别

上一篇中我们对训练数据做了一些预处理，检测出人脸并保存在\pic\color\x文件夹下（x=1,2,3,...类别号），本文做训练和识别。为了识别，首先将人脸训练数据 转为灰度、对齐、归一化，再放入分类器（EigenFaceRecognizer）,最后用训练出的model进行predict。

-----------------------------------------

环境：vs2010+opencv 2.4.6.0

特征：eigenface

Input：一个人脸数据库，15个人，每人20个样本（左右）。

Output：人脸检测，并识别出每张检测到的人脸。

-----------------------------------------

1. 为训练数据预处理（ 转为灰度、对齐、归一化 ）

• 转为灰度和对齐是后面做训练时EigenFaceRecognizer的要求；
• 归一化是防止光照带来的影响

在上一篇的 2.2 Prehelper.cpp文件中加入函数

void resizeandtogray(char* dir,int k,  vector &images, vector &labels,
vector &testimages, vector &testlabels);

 void resizeandtogray(char* dir,int K, vector &images, vector<int> &labels,
     vector &testimages, vector<int> &testlabels)
 {
     IplImage* standard = cvLoadImage("D:\\privacy\\picture\\photo\\2.jpg",CV_LOAD_IMAGE_GRAYSCALE);
     string cur_dir;
     char id[5];
     int i,j;
     for(int i=1; i<=K; i++)
     {
         cur_dir = dir;
         cur_dir.append("gray\\");
         _itoa(i,id,10);
         cur_dir.append(id);
         const char* dd = cur_dir.c_str();
         CStatDir statdir;
         if (!statdir.SetInitDir(dd))
         {
             puts("Dir not exist");
             return;
         }
         cout<<"Processing samples in Class "<
         vector<char*>file_vec = statdir.BeginBrowseFilenames("*.*");
         for (j=0;j
         {
             IplImage* cur_img = cvLoadImage(file_vec[j],CV_LOAD_IMAGE_GRAYSCALE);
             cvResize(cur_img,standard,CV_INTER_AREA);
             Mat cur_mat = cvarrToMat(standard,true),des_mat;
             cv::normalize(cur_mat,des_mat,0, 255, NORM_MINMAX, CV_8UC1);
             cvSaveImage(file_vec[j],cvCloneImage(&(IplImage) des_mat));
             if(j!=file_vec.size())
             {
                     images.push_back(des_mat);
                     labels.push_back(i);
             }
             else
             {
                 testimages.push_back(des_mat);
                 testlabels.push_back(i);
             }
         }
         cout<" images."<
     }
 }

并在main中调用：

 int main( )
 {
     CvCapture* capture = 0;
     Mat frame, frameCopy, image;
     string inputName;
     int mode;

     char dir[256] = "D:\\Courses\\CV\\Face_recognition\\pic\\";
     //preprocess_trainingdata(dir,K); //face_detection and extract to file
     vector images,testimages;
     vector<int> labels,testlabels;
     resizeandtogray(dir,K,images,labels,testimages,testlabels); //togray, normalize and resize

     system("pause");
     return 0;
 }

2. 训练

有了vector images,testimages; vector labels,testlabels; 可以开始训练了，我们采用EigenFaceRecognizer建模。

在Prehelper.cpp中加入函数

Ptr Recognition(vector images, vector labels,vector testimages, vector testlabels)；

 Ptr Recognition(vector images, vector<int> labels,
     vector testimages, vector<int> testlabels)
 {
     Ptr model = createEigenFaceRecognizer(10);//10 Principal components
     cout<<"train"<
     model->train(images,labels);
     int i,acc=0,predict_l;
     for (i=0;i
     {
         predict_l = model->predict(testimages[i]);
         if(predict_l != testlabels[i])
         {
             cout<<"An error in recognition: sample "<", predict "<<
                 predict_l<<", groundtruth "<
             imshow("error 1",testimages[i]);
             waitKey();
         }
         else
             acc++;
     }
     cout<<"Recognition Rate: "<
     return model;
 }

Recognization()输出分错的样本和正确率，最后返回建模结果Ptr model

主函数改为：

 int main( )
 {
     CvCapture* capture = 0;
     Mat frame, frameCopy, image;
     string inputName;
     int mode;

     char dir[256] = "D:\\Courses\\CV\\Face_recognition\\pic\\";
     //preprocess_trainingdata(dir,K); //face_detection and extract to file
     vector images,testimages;
     vector<int> labels,testlabels;
     //togray, normalize and resize; load to images,labels,testimages,testlabels
     resizeandtogray(dir,K,images,labels,testimages,testlabels);
     //recognition
     Ptr model = Recognition(images,labels,testimages,testlabels);
     char* dirmodel = new char [256];
     strcpy(dirmodel,dir); strcat(dirmodel,"model.out");
     FILE* f = fopen(dirmodel,"w");
     fwrite(model,sizeof(model),1,f);
     system("pause");
     return 0;
 }

最终结果：一个错分样本，正确率93.3%

文章所用代码打包链接：http://download.csdn.net/detail/abcjennifer/7047853

from: http://blog.csdn.net/abcjennifer/article/details/20446077