Dlib庫(kù)中提供了正臉人臉關(guān)鍵點(diǎn)檢測(cè)的接口，這里參考dlib/examples/face_landmark_detection_ex.cpp中的代碼，通過(guò)調(diào)用Dlib中的接口，實(shí)現(xiàn)正臉人臉關(guān)鍵點(diǎn)檢測(cè)的測(cè)試代碼，測(cè)試代碼如下：

/* reference: dlib/examples/face_landmark_detection_ex.cppThis program shows how to find frontal human faces in an image andestimate their pose.  The pose takes the form of 68 landmarks.  These arepoints on the face such as the corners of the mouth, along the eyebrows, onthe eyes, and so forth
*/
int test_face_landmark()
{// download: http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2const std::string shape_predictor_68_face_landmarks = "E:/GitCode/Face_Test/src/dlib/data/shape_predictor_68_face_landmarks.dat";// We need a face detector.  We will use this to get bounding boxes for// each face in an image.dlib::frontal_face_detector detector = dlib::get_frontal_face_detector();// And we also need a shape_predictor.  This will predict face// landmark positions given an image and face bounding boxdlib::shape_predictor sp;dlib::deserialize(shape_predictor_68_face_landmarks) >> sp;std::vector<std::string> images{ "1.jpg", "2.jpg", "3.jpg", "4.jpeg", "5.jpeg", "6.jpg", "7.jpg", "8.jpg", "9.jpg", "10.jpg","11.jpeg", "12.jpg", "13.jpeg", "14.jpg", "15.jpeg", "16.jpg", "17.jpg", "18.jpg", "19.jpg", "20.jpg" };std::vector<int> count_faces{ 1, 2, 6, 0, 1, 1, 1, 2, 1, 1,1, 1, 1, 1, 1, 1, 1, 0, 8, 2 };std::string path_images{ "E:/GitCode/Face_Test/testdata/" };if (images.size() != count_faces.size()) {fprintf(stderr, "their size that images and count_faces are mismatch\n");return -1;}for (int i = 0; i < images.size(); i++) {cv::Mat matSrc = cv::imread(path_images + images[i], 1);if (matSrc.empty()) {fprintf(stderr, "read image error: %s\n", images[i].c_str());return -1;}dlib::array2d<unsigned char> img;dlib::load_image(img, path_images + images[i]);// Make the image larger so we can detect small faces.pyramid_up(img);// Now tell the face detector to give us a list of bounding boxes// around all the faces it can find in the image.std::vector<dlib::rectangle> dets = detector(img);fprintf(stderr, "detect face count: %d, actual face count: %d\n", dets.size(), count_faces[i]);// Now we will go ask the shape_predictor to tell us the pose of// each face we detected.std::vector<dlib::full_object_detection> shapes;for (unsigned long j = 0; j < dets.size(); ++j) {dlib::full_object_detection shape = sp(img, dets[j]);fprintf(stderr, "landmark num: %d\n", shape.num_parts());dlib::rectangle rect = shape.get_rect();fprintf(stderr, "rect: left = %d, top = %d, width = %d, height = %d\n", rect.left() / 2, rect.top() / 2, rect.width() / 2, rect.height() / 2);cv::rectangle(matSrc, cv::Rect(rect.left() / 2, rect.top() / 2, rect.width() / 2, rect.height() / 2), cv::Scalar(0, 255, 0), 2);for (int pt = 0; pt < shape.num_parts(); pt++) {cv::circle(matSrc, cv::Point(shape.part(pt).x() / 2, shape.part(pt).y() / 2), 1, cv::Scalar(0, 0, 255), 2);}}std::string save_result = path_images + "_" + images[i];cv::imwrite(save_result, matSrc);}int width = 200;int height = 200;cv::Mat dst(height * 5, width * 4, CV_8UC3);for (int i = 0; i < images.size(); i++) {std::string input_image = path_images + "_" + images[i];cv::Mat src = cv::imread(input_image, 1);if (src.empty()) {fprintf(stderr, "read image error: %s\n", images[i].c_str());return -1;}cv::resize(src, src, cv::Size(width, height), 0, 0, 4);int x = (i * width) % (width * 4);int y = (i / 4) * height;cv::Mat part = dst(cv::Rect(x, y, width, height));src.copyTo(part);}std::string output_image = path_images + "result.png";cv::imwrite(output_image, dst);return 0;
}

? 執(zhí)行結(jié)果如下圖：

? 人臉關(guān)鍵點(diǎn)檢測(cè)結(jié)果如下：

? GitHub：https://github.com/fengbingchun/Face_Test

總結(jié)

以上是生活随笔為你收集整理的Dlib库中实现正脸人脸关键点(landmark)检测的测试代码的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。