dlib人脸训练和关键点检测

总述：此例子是根据dlib两个关键的例子

1.训练：train_shape_predictor_ex.cpp

2.关键点检测：face_landmark_detection_ex

相关代码如下：

#include "stdafx.h"
#include <dlib/image_processing.h>
#include <dlib/data_io.h>
#include <iostream>
#include <dlib/image_processing/frontal_face_detector.h>
#include <dlib/image_processing/render_face_detections.h>
#include <dlib/image_processing.h>
#include <dlib/gui_widgets.h>
#include <dlib/image_io.h>

using namespace dlib;
using namespace std;

double interocular_distance(
    const full_object_detection& det
    )
{
    dlib::vector<double, 2> l, r;
    double cnt = 0;
    // Find the center of the left eye by averaging the points around 
    // the eye.
    for (unsigned long i = 36; i <= 41; ++i)
    {
        l += det.part(i);
        ++cnt;
    }
    l /= cnt;

    // Find the center of the right eye by averaging the points around 
    // the eye.
    cnt = 0;
    for (unsigned long i = 42; i <= 47; ++i)
    {
        r += det.part(i);
        ++cnt;
    }
    r /= cnt;

    // Now return the distance between the centers of the eyes
    return length(l - r);
}

std::vector<std::vector<double> > get_interocular_distances(
    const std::vector<std::vector<full_object_detection> >& objects
    )
{
    std::vector<std::vector<double> > temp(objects.size());
    for (unsigned long i = 0; i < objects.size(); ++i)
    {
        for (unsigned long j = 0; j < objects[i].size(); ++j)
        {
            temp[i].push_back(interocular_distance(objects[i][j]));
        }
    }
    return temp;
}

//训练函数
void train(){
    try
    {
        //一、preprocessing
        //1. 载入训练集，测试集
        const std::string faces_directory = "faces";
        dlib::array<array2d<unsigned char> > images_train, images_test;
        std::vector<std::vector<full_object_detection> > faces_train, faces_test;

        load_image_dataset(images_train, faces_train, faces_directory + "/training_with_face_landmarks.xml");
        load_image_dataset(images_test, faces_test, faces_directory + "/testing_with_face_landmarks.xml");

        // 二、training
        //1. 定义trainer类型
        shape_predictor_trainer trainer;
        //设置训练参数
        trainer.set_oversampling_amount(300); 
        trainer.set_nu(0.05);
        trainer.set_tree_depth(2);
        trainer.be_verbose();

        // 2. 训练，生成人脸关键点检测器
        shape_predictor sp = trainer.train(images_train, faces_train);


        // 三、测试
        cout << "mean training error: " <<
            test_shape_predictor(sp, images_train, faces_train, get_interocular_distances(faces_train)) << endl;
        cout << "mean testing error:  " <<
            test_shape_predictor(sp, images_test, faces_test, get_interocular_distances(faces_test)) << endl;

        // 四、存储
        serialize("sp.dat") << sp;
    }
    catch (exception& e)
    {
        cout << "
exception thrown!" << endl;
        cout << e.what() << endl;
    }
}

//关键点检测函数
int main(int argc, char** argv)
{
     try
    {
             
        frontal_face_detector detector = get_frontal_face_detector();
        shape_predictor sp;
        //将上一步训练好的sp.dat 载入
        deserialize("sp.dat") >> sp;
        image_window win, win_faces;
           const std::string image = "faces/2007_007763.jpg";
        cout << "processing image " << image << endl;
        array2d<rgb_pixel> img;
        load_image(img, image);
            // 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 in the image.
            std::vector<rectangle> dets = detector(img);
            cout << "Number of faces detected: " << dets.size() << endl;

            // Now we will go ask the shape_predictor to tell us the pose of
            // each face we detected.
            std::vector<full_object_detection> shapes;
            for (unsigned long j = 0; j < dets.size(); ++j)
            {
                full_object_detection shape = sp(img, dets[j]);
                cout << "number of parts: "<< shape.num_parts() << endl;
                cout << "pixel position of first part:  " << shape.part(0) << endl;
                cout << "pixel position of second part: " << shape.part(1) << endl;
                // You get the idea, you can get all the face part locations if
                // you want them.  Here we just store them in shapes so we can
                // put them on the screen.
                shapes.push_back(shape);
            }

            // Now let's view our face poses on the screen.
            win.clear_overlay();
            win.set_image(img);
            win.add_overlay(render_face_detections(shapes));

            // We can also extract copies of each face that are cropped, rotated upright,
            // and scaled to a standard size as shown here:
            dlib::array<array2d<rgb_pixel> > face_chips;
            extract_image_chips(img, get_face_chip_details(shapes), face_chips);
            win_faces.set_image(tile_images(face_chips));

            cout << "Hit enter to process the next image..." << endl;
            cin.get();
        
    }
    catch (exception& e)
    {
        cout << "
exception thrown!" << endl;
        cout << e.what() << endl;
    }
}