匹配臉

匹配臉

原創

zqlanwei

2020-02-21 17:54

這個程序是由多張人臉生成特徵臉

#if 1

#include <opencv2\contrib\contrib.hpp>
#include <opencv2\core\core.hpp>
#include <opencv2\highgui\highgui.hpp>

#include <iostream>
#include <fstream>
#include <sstream>

using namespace std;
using namespace cv;

static Mat norm_0_255(cv::InputArray _src)
{
Mat src = _src.getMat();
Mat dst;

switch(src.channels())
{
case 1:
  cv::normalize(_src, dst, 0, 255, cv::NORM_MINMAX, CV_8UC1);
  break;
case 3:
  cv::normalize(_src, dst, 0, 255, cv::NORM_MINMAX, CV_8UC3);
  break;
default:
  src.copyTo(dst);
  break;
}

return dst;
}

static void read_csv(const string &filename, vector<Mat> &images, vector<int> &labels, char separator = ';')
{
std::ifstream file(filename.c_str(), ifstream::in);
if(!file)
{
string error_message = "No valid input file was given.";
CV_Error(CV_StsBadArg, error_message);
}

string line, path, classlabel;
while(getline(file, line))
{
  stringstream liness(line);
  getline(liness, path, separator); //遇到分號就結束
  getline(liness, classlabel);     //繼續從分號後面開始，遇到換行結束
  if(!path.empty() && !classlabel.empty())
  {
   images.push_back(imread(path, 0));
   labels.push_back(atoi(classlabel.c_str()));
  }
}
}

int main(int argc, char *argv[])
{
string output_folder;
output_folder = string("D:\\ORL\\result");

//讀取你的CSV文件路徑
string fn_csv = string("D:\\ORL\\to\\at.txt");

//兩個容器來存放圖像數據和對應的標籤
vector<Mat> images;
vector<int> labels;

try
{
  read_csv(fn_csv, images, labels);
}
catch(cv::Exception &e)
{
  cerr<<"Error opening file "<<fn_csv<<". Reason: "<<e.msg<<endl;
  exit(1);
}

//如果沒有讀到足夠的圖片，就退出
if(images.size() <= 1)
{
string error_message = "This demo needs at least 2 images to work.";
CV_Error(CV_StsError, error_message);
}

//得到第一張照片的高度，在下面對圖像變形到他們原始大小時需要
int height = images[0].rows;

//移除最後一張圖片，用於做測試
Mat testSample = images[images.size() - 1];
cv::imshow("testSample", testSample);
int testLabel = labels[labels.size() - 1];

images.pop_back();
labels.pop_back();

/*
* 下面創建一個特徵臉模型用於人臉識別，
* 通過CSV文件讀取的圖像和標籤訓練它。
*/

cv::Ptr<cv::FaceRecognizer> model = cv::createEigenFaceRecognizer();
model->train(images, labels);

/*
* 下面對測試圖像進行預測，predictedLabel 是預測標籤結果
*/
int predictedLabel = model->predict(testSample);

string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
cout<<result_message<<endl;

//獲取特徵臉模型的特徵值的例子，使用了getMat方法
Mat eigenvalues = model->getMat("eigenvalues");
//獲取特徵向量
Mat W = model->getMat("eigenvectors");

//得到訓練圖像的均值向量
Mat mean = model->getMat("mean");

imshow("mean", norm_0_255(mean.reshape(1, images[0].rows)));
cv::imwrite(format("%s/mean.png", output_folder.c_str()), norm_0_255(mean.reshape(1, images[0].rows)));

//實現並保存特徵臉
for(int i=0; i <min(10, W.cols); i++)
{
string msg = format("Eigenvalue #%d = %.5f", i, eigenvalues.at<double>(i));
cout<<msg<<endl;

Mat ev = W.col(i).clone();

//把他變成原始大小，爲了把數據顯示歸一化到0-255.
Mat grayscale = norm_0_255(ev.reshape(1,height));

  //使用僞彩色來顯示結果
  Mat cgrayscale;
  cv::applyColorMap(grayscale, cgrayscale, COLORMAP_JET);

  imshow(format("eigenface_%d", i), cgrayscale);
  imwrite(format("%s/eigenface_%d.png", output_folder.c_str(), i), cgrayscale);
}

//在預測過程中，顯示並保存重建後的圖片
for(int num_components = 10; num_components < 390; num_components += 15)
{
  //從模型中的特徵向量截取一部分
  Mat evs = Mat(W, Range::all(), Range(0, num_components));
  //投影
  Mat projection = cv::subspaceProject(evs, mean, images[0].reshape(1,1));
  //重構
  Mat reconstruction = cv::subspaceReconstruct(evs, mean, projection);

reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));

imshow(format("eigenface_reconstruction_%d", num_components),reconstruction);
imwrite(format("%s/eigenface_reconstruction_%d.png", output_folder.c_str(),num_components), reconstruction);

}

cv::waitKey(0);
return 0;
}

#endif