I have a video stream that detects faces using openCV, how could I then capture the face closest to the camera and save it to an image file?

Question

So I want the face which is most prominent to be captured as an image file.

Here is the detection code below:

void detectAndDisplay(Mat frame) 
{ 
std::vector<Rect> faces;
Mat gray;

cvtColor(frame, gray, CV_BGR2GRAY);
equalizeHist(gray,gray);
//find faces
face_cascade.detectMultiScale(gray, faces, 1.1, 2, 0 | CV_HAAR_SCALE_IMAGE, Size(30, 30));

for (size_t i = 0; i < faces.size(); i++)
{
    Point center(faces[i].x + faces[i].width*0.5, faces[i].y + faces[i].height*0.5);
    //draw around the face
    ellipse(frame, center, Size(faces[i].width*0.5, faces[i].height*0.5), 0, 0, 360, Scalar(255,      255, 255), 4, 8, 0);

    Mat faceROI = gray(faces[i]);

}
imshow(window_name, frame);

}

Answer 1

如果检测到的面部的大小足以描述其突出程度（实际上不是），则由于faces每个元素都是Rect ，您可以使用Rect::area()作为度量。