c++ - 即使检测到人脸并正确获取左右两半，OpenCV 也没有检测到眼睛
问题描述
我试图在我的代码中找到问题并理解与 opencv 和面部/眼睛检测相关的问题。完整代码在这里：
代码块中的代码是问题所在的浓缩（比较）。
//Search for both eyes within the given face image. Returns the eye centers in 'leftEye' and 'rightEye',
// or sets them to (-1,-1) if each eye was not found. Note that you can pass a 2nd eyeCascade if you
// want to search eyes using 2 different cascades. For example, you could use a regular eye detector
// as well as an eyeglasses detector, or a left eye detector as well as a right eye detector.
// Or if you don't want a 2nd eye detection, just pass an uninitialized CascadeClassifier.
// Can also store the searched left & right eye regions if desired.
void detectBothEyes(const Mat &face, CascadeClassifier &eyeCascade1,
CascadeClassifier &eyeCascade2,
Point &leftEye, Point &rightEye,
Rect *searchedLeftEye,
Rect *searchedRightEye,
String filename) {
//For default eye.xml or eyeglasses.xml: Finds both eyes in
// roughly 40% of detected faces, but does not detect closed eyes.
const float EYE_SX = 0.16f;
const float EYE_SY = 0.26f;
const float EYE_SW = 0.30f;
const float EYE_SH = 0.28f;
int leftX = cvRound(face.cols * EYE_SX);
int topY = cvRound(face.rows * EYE_SY);
int widthX = cvRound(face.cols * EYE_SW);
int heightY = cvRound(face.rows * EYE_SH);
int rightX = cvRound(face.cols * (1.0-EYE_SX-EYE_SW) ); //Start of right-eye corner
Mat topLeftOfFace = face(Rect(leftX, topY, widthX, heightY));
Mat topRightOfFace = face(Rect(rightX, topY, widthX, heightY));
Rect leftEyeRect, rightEyeRect;
imwrite(filename + "_leftHalfFace.png",topLeftOfFace);
imwrite(filename + "_rightHalfFace.png",topRightOfFace);
//Search the left region, then the right region using the 1st eye detector.
detectLargestObject(topLeftOfFace, eyeCascade1, leftEyeRect,
topLeftOfFace.cols);
cout << "leftEyeRect= "<< endl << " " << leftEyeRect << endl << endl;
detectLargestObject(topRightOfFace, eyeCascade1, rightEyeRect,
topRightOfFace.cols);
cout << "rightEyeRect= "<< endl << " " << rightEyeRect << endl << endl;
//NOTE...there is code here that says if leftEyeRect or rightEyeDetect was not
// detected to set
// to (-1,-1)
}
代码是c++。该代码是从一本书中提供的示例代码修改而来的。
我正在尝试读取图像并检测面部和眼睛（以及面部识别）。在我尝试检测的 20 张图像（10 张汤姆克鲁斯和 10 张艾玛沃特森）上，人脸检测似乎始终成功。但是，即使我能够成功地将检测到的人脸分成左右两半（每一半都显示适当的眼睛），眼睛检测对于几张图像都失败了。我不明白为什么以及我能做些什么来解决这个问题？
具体问题出在函数 detectBothEyes 中，其中变量 leftEyeRect 和 rightEyeRect 都返回 (-1, -1)（意味着它没有找到眼睛）。
谁能指出我的问题或如何改善对眼睛的检测？
我希望检测到眼睛，因此变量“leftEyeRect”和“rightEyeRect”不是（-1，-1）而是正值）。