使用dlib基于CNN(卷积神经网络)的人脸检测器来检测人脸

基于机器学习CNN方法来检测人脸比之前介绍的效率要慢很多

需要先下载一个训练好的模型数据：

地址点击下载

// dlib_cnn_facedetect.cpp: 定义控制台应用程序的入口点。

//

#include "stdafx.h"

#include <iostream>

#include <dlib/dnn.h>

#include <dlib/data_io.h>

#include <dlib/image_processing.h>

#include <dlib/gui_widgets.h>

using namespace std;

using namespace dlib;

// ----------------------------------------------------------------------------------------

template <long num_filters, typename SUBNET> using con5d = con<num_filters, , , , , SUBNET>;

template <long num_filters, typename SUBNET> using con5 = con<num_filters, , , , , SUBNET>;

template <typename SUBNET> using downsampler = relu<affine<con5d<, relu<affine<con5d<, relu<affine<con5d<, SUBNET>>>>>>>>>;

template <typename SUBNET> using rcon5 = relu<affine<con5<, SUBNET>>>;

using net_type = loss_mmod<con<, , , , , rcon5<rcon5<rcon5<downsampler<input_rgb_image_pyramid<pyramid_down<>>>>>>>>;

// ----------------------------------------------------------------------------------------

int main(int argc, char** argv)

{

    try {

        if (argc == )

        {

            cout << "Call this program like this:" << endl;

            cout << "./dnn_mmod_face_detection_ex mmod_human_face_detector.dat faces/*.jpg" << endl;

            cout << "\nYou can get the mmod_human_face_detector.dat file from:\n";

            cout << "http://dlib.net/files/mmod_human_face_detector.dat.bz2" << endl;

            return ;

        }

        net_type net;

        deserialize(argv[]) >> net;

        image_window win;

        for (int i = ; i < argc; ++i)

        {

            matrix<rgb_pixel> img;

            load_image(img, argv[i]);

            // Upsampling the image will allow us to detect smaller faces but will cause the

            // program to use more RAM and run longer.

            while (img.size() <  * )

                pyramid_up(img);

            // Note that you can process a bunch of images in a std::vector at once and it runs

            // much faster, since this will form mini-batches of images and therefore get

            // better parallelism out of your GPU hardware.  However, all the images must be

            // the same size.  To avoid this requirement on images being the same size we

            // process them individually in this example.

            auto dets = net(img);

            win.clear_overlay();

            win.set_image(img);

            for (auto&& d : dets)

                win.add_overlay(d);

            cout << "Hit enter to process the next image." << endl;

            cin.get();

        }

    }

    catch (std::exception& e)

    {

        cout << e.what() << endl;

    }

}