Realization of mask recognition based on OpenCV

Then the first step to do , Is to train the classifier we need , I choose OpenCV in ml Modular SVM Classifier to train mask recognition classifier . The code for the training section is as follows ：

string positive_path = "D:\\opencv_c++\\opencv_tutorial\\data\\test\\positive\\";
  string negative_path = "D:\\opencv_c++\\opencv_tutorial\\data\\test\\negative\\";
  
  vector<string> positive_images_str, negative_images_str;
  glob(positive_path, positive_images_str);
  glob(negative_path, negative_images_str);
  
  vector<Mat>positive_images, negative_images;
  for (int i = 0; i < positive_images_str.size(); i++)
  {
    
    Mat positive_image = imread(positive_images_str[i]);
    
    positive_images.push_back(positive_image);
  }
  for (int j = 0; j < negative_images_str.size(); j++)
  {
    
    Mat negative_image = imread(negative_images_str[j]);
    
    negative_images.push_back(negative_image);
  }
  string savePath = "face_mask_detection.xml";
  trainSVM(positive_images, negative_images, savePath);

First read all training images , Contains positive samples （ Wear a mask ） Images and negative samples （ Don't wear a mask ） Images , Then pack the positive and negative sample sets into vector type , Pass in the training function trainSVM() in , This function is defined in the header file “face_mask.h” in .

In the process of training , We are not training by fully unfolding the image , But through feature extraction , Get the image of each sample HOG features , Recalculate each HOG Feature descriptor of feature , Train through feature descriptors SVM classifier .

It should be noted that , We are not doing a complete sample image HOG Feature extraction and description , Instead, the face region of the sample image is extracted first , The extracted face region image is then HOG Feature extraction and description and training .

meanwhile , You also need to label the positive and negative sample sets , Positive samples are marked as 1, Negative samples are marked as -1.

The code is as follows ：

for (int i = 0; i < positive_num; i++)
  {
    
    Mat positive_face;
    Rect positive_faceBox;
    if (faceDetected(positive_images[i], positive_face, positive_faceBox))
    {
    
      resize(positive_face, positive_face, Size(64, 128));
      Mat gray;
      cvtColor(positive_face, gray, COLOR_BGR2GRAY);      
      vector<float> descriptor;
      hog_train->compute(gray, descriptor);
      train_descriptors.push_back(descriptor);
      labels.push_back(1);
    }
  }
  for (int j = 0; j < negative_num; j++)
  {
    
    Mat negative_face;
    Rect negative_faceBox;
    if (faceDetected(negative_images[j], negative_face, negative_faceBox))
    {
    
      resize(negative_face, negative_face, Size(64, 128));
      Mat gray;
      cvtColor(negative_face, gray, COLOR_BGR2GRAY);
      vector<float> descriptor;
      hog_train->compute(gray, descriptor);
      train_descriptors.push_back(descriptor);
      labels.push_back(-1);
    }
  }
  
  int width = train_descriptors[0].size();
  int height = train_descriptors.size();
  Mat train_data = Mat::zeros(Size(width, height), CV_32F);
  for (int r = 0; r < height; r++)
  {
    
    for (int c = 0; c < width; c++)
    {
    
      train_data.at<float>(r, c) = train_descriptors[r][c];
    }
  }
  auto train_svm = ml::SVM::create();
  train_svm->trainAuto(train_data, ml::ROW_SAMPLE, labels);
  train_svm->save(path);
  hog_train->~HOGDescriptor();
  train_svm->clear();

The function for face extraction faceDetected() Definition in header file “face.h” in . Here we use opencv_face_detector_uint8.pb Face detection model .

So at this point , It realizes the detection of whether to wear a mask SVM Training of classifiers , The model files obtained from training are as follows ：

Next , We are going to load this xml File and detect the input image . among , The function used for detection is FaceMaskDetect(), This function is defined in “face_mask.h” Header file .

auto detecModel = ml::SVM::load("face_mask_detection.xml");
Mat test_image = imread("D:/BaiduNetdiskDownload/ Face mask detection data set /val/test_00004577.jpg");
FaceMaskDetect(test_image, detecModel);
  
imshow("test_image", test_image);

Come here , We achieved from training , To the process of running detection , Let's see how the operation works ：

First look at the image without mask , If it is detected that the mask is not worn , Then the face is framed in red , And marked red “ Not Face Mask ” word :