dlib 04 dlib自带demo 基于HOG的人脸特征检测

01 dlib的fhog人脸检测器训练资源

dlib提供了fhog的人脸图片及对应的数据文件。
代码:dlib\examples\fhog_object_detector_ex.cpp
工程名:fhog_object_detector_ex
测试数据:dlib\examples\faces
训练数据集图片
dlib\examples\faces\training.xml
dlib\examples\faces\2007_007763.jpg
dlib\examples\faces\2008_001009.jpg
dlib\examples\faces\2008_001322.jpg
dlib\examples\faces\2008_002079.jpg
测试数据及图片
dlib\examples\faces\testing.xml
dlib\examples\faces\2008_002470.jpg
dlib\examples\faces\2008_002506.jpg
dlib\examples\faces\2008_004176.jpg
dlib\examples\faces\2008_007676.jpg
dlib\examples\faces\2009_004587.jpg

02 项目设置

把examples解决方案中的fhog_object_detector_ex工程设置为启动项。

配置属性==>调试==>命令参数==>..\..\..\examples\faces
配置属性==>调试==>工作目录==>$(OutDir)

03 运行训练效果

04 参考

http://blog.csdn.net/u014365862/article/details/53338999
http://blog.csdn.net/qq_14845119/article/details/52625426
http://blog.csdn.net/elaine_bao/article/details/53046542

05 主要代码

dlib\examples\fhog_object_detector_ex.cpp

int main(int argc, char** argv)
{

    try
    {
        //一、preprocessing
        //1. 载入训练集，测试集
        const std::string faces_directory = "faces";
        dlib::arrayunsigned char> > images_train, images_test;
        std::vector<std::vector > face_boxes_train, face_boxes_test;

        load_image_dataset(images_train, face_boxes_train, faces_directory + "/training.xml");
        load_image_dataset(images_test, face_boxes_test, faces_directory + "/testing.xml");

        //2.图片上采样
        upsample_image_dataset2> >(images_train, face_boxes_train);
        upsample_image_dataset2> >(images_test, face_boxes_test);

        //3.训练图片做镜像处理，扩充训练集
        add_image_left_right_flips(images_train, face_boxes_train);

        //二、training
        //1.定义scanner类型，用于扫描图片并提取特征（HOG）
        typedef scan_fhog_pyramid6> > image_scanner_type;
        image_scanner_type scanner;

        //2. 设置scanner扫描窗口大小
        scanner.set_detection_window_size(80, 80);

        //3.定义trainer类型（SVM），用于训练人脸检测器                
    structural_object_detection_trainer trainer(scanner);
        // Set this to the number of processing cores on your machine.
        trainer.set_num_threads(4);
        // 设置SVM的参数C，C越大表示更好地去拟合训练集，当然也有可能造成过拟合。通过尝试不同C在测试集上的效果得到最佳值
        trainer.set_c(1); 
        trainer.be_verbose();
        //设置训练结束条件，"risk gap"<0.01时训练结束，值越小表示SVM优化问题越精确，训练时间也会越久。
        //通常取0.1-0.01.在verbose模式下每一轮的risk gap都会打印出来。
        trainer.set_epsilon(0.01);

        //4.训练，生成object_detector
        object_detector detector = trainer.train(images_train, face_boxes_train);

        //三、测试
        // 输出precision, recall, average precision.
        cout << "training results: " << test_object_detection_function(detector, images_train, face_boxes_train) << endl;
        cout << "testing results:  " << test_object_detection_function(detector, images_test, face_boxes_test) << endl;

        //显示hog
        image_window hogwin(draw_fhog(detector), "Learned fHOG detector");

        // 显示测试集的人脸检测结果
        image_window win;
        for (unsigned long i = 0; i < images_test.size(); ++i)
        {
            // Run the detector and get the face detections.
            std::vector dets = detector(images_test[i]);
            win.clear_overlay();
            win.set_image(images_test[i]);
            win.add_overlay(dets, rgb_pixel(255, 0, 0));
            cout << "Hit enter to process the next image..." << endl;
            cin.get();
        }

        //四、模型存储
        serialize("face_detector.svm") << detector;
        // you can recall it using the deserialize() function.
        object_detector detector2;
        deserialize("face_detector.svm") >> detector2;
    }
    catch (exception& e)
    {
        cout << "\nexception thrown!" << endl;
        cout << e.what() << endl;
    }
}