Revision history [back]

#include "stdafx.h"
#include "TrainHOGEx.h"


TrainHOGEx::TrainHOGEx()
{
}


TrainHOGEx::~TrainHOGEx()
{
}
int mainTestEx();
void get_svm_detectorex(const Ptr< SVM > & svm, vector< float > & hog_detector);
void convert_to_mlex(const std::vector< Mat > & train_samples, Mat& trainData);
void load_images(const String & dirname, vector< Mat > & img_lst, bool showImages);
void sample_negex(const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst, const Size & size);
void computeHOGs(const Size wsize, const vector< Mat > & img_lst, vector< Mat > & gradient_lst);
int test_trained_detector(String obj_det_filename, String test_dir, String videofilename);

void get_svm_detectorex(const Ptr< SVM >& svm, vector< float > & hog_detector)
{
    // get the support vectors
    Mat sv = svm->getSupportVectors();
    const int sv_total = sv.rows;
    // get the decision function
    Mat alpha, svidx;
    double rho = svm->getDecisionFunction(0, alpha, svidx);

    CV_Assert(alpha.total() == 1 && svidx.total() == 1 && sv_total == 1);
    CV_Assert((alpha.type() == CV_64F && alpha.at<double>(0) == 1.) ||
        (alpha.type() == CV_32F && alpha.at<float>(0) == 1.f));
    CV_Assert(sv.type() == CV_32F);
    hog_detector.clear();

    hog_detector.resize(sv.cols + 1);
    memcpy(&hog_detector[0], sv.ptr(), sv.cols * sizeof(hog_detector[0]));
    hog_detector[sv.cols] = (float)-rho;
}

/*
* Convert training/testing set to be used by OpenCV Machine Learning algorithms.
* TrainData is a matrix of size (#samples x max(#cols,#rows) per samples), in 32FC1.
* Transposition of samples are made if needed.
*/
void convert_to_mlex(const vector< Mat > & train_samples, Mat& trainData)
{
    //--Convert data
    const int rows = (int)train_samples.size();
    const int cols = (int)std::max(train_samples[0].cols, train_samples[0].rows);
    Mat tmp(1, cols, CV_32FC1); //< used for transposition if needed
    trainData = Mat(rows, cols, CV_32FC1);

    for (size_t i = 0; i < train_samples.size(); ++i)
    {
        CV_Assert(train_samples[i].cols == 1 || train_samples[i].rows == 1);

        if (train_samples[i].cols == 1)
        {
            transpose(train_samples[i], tmp);
            tmp.copyTo(trainData.row((int)i));
        }
        else if (train_samples[i].rows == 1)
        {
            train_samples[i].copyTo(trainData.row((int)i));
        }
    }
}

void load_images(const String & dirname, vector< Mat > & img_lst, bool showImages = false)
{
    try {
        vector< String > files;
        try {
            glob(dirname, files);
        }
        catch (...)
        {
            AfxMessageBox("exception");
        }

        for (size_t i = 0; i < files.size(); ++i)
        {
            Mat img = imread(files[i]); // load the image
            if (img.empty())            // invalid image, skip it.
            {
                cout << files[i] << " is invalid!" << endl;
                continue;
            }

            if (showImages)
            {
                imshow("image", img);
                waitKey(1);
            }
            img_lst.push_back(img);
        }
    }
    catch (...)
    {
        AfxMessageBox("exception");
    }
}

void sample_negex(const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst, const Size & size)
{
    Rect box;
    box.width = size.width;
    box.height = size.height;

    const int size_x = box.width;
    const int size_y = box.height;

    srand((unsigned int)time(NULL));

    for (size_t i = 0; i < full_neg_lst.size(); i++)
    {
        box.x = rand() % (full_neg_lst[i].cols - size_x);
        box.y = rand() % (full_neg_lst[i].rows - size_y);
        Mat roi = full_neg_lst[i](box);
        neg_lst.push_back(roi.clone());
    }
}

void computeHOGs(const Size wsize, const vector< Mat > & img_lst, vector< Mat > & gradient_lst)
{
    HOGDescriptor hog;
    hog.winSize = wsize;

    Rect r = Rect(0, 0, wsize.width, wsize.height);
    r.x += (img_lst[0].cols - r.width) / 2;
    r.y += (img_lst[0].rows - r.height) / 2;

    Mat gray;
    vector< float > descriptors;

    for (size_t i = 0; i < img_lst.size(); i++)
    {
            cvtColor(img_lst[i](r), gray, COLOR_BGR2GRAY);
            hog.compute(gray, descriptors, Size(8, 8), Size(0, 0));
            gradient_lst.push_back(Mat(descriptors).clone());
    }
}

int test_trained_detector(String obj_det_filename, String test_dir, String videofilename)
{
    cout << "Testing trained detector..." << endl;
    HOGDescriptor hog;
    hog.load(obj_det_filename);

    vector< String > files;
    glob(test_dir, files);

    int delay = 0;


    obj_det_filename = "testing " + obj_det_filename;
    namedWindow(obj_det_filename, WINDOW_NORMAL);

    for (size_t i = 0;; i++)
    {
        Mat img;

        if (i < files.size())
        {
            img = imread(files[i]);
        }

        if (img.empty())
        {
            return 0;
        }

        vector< Rect > detections;
        vector< double > foundWeights;

        hog.detectMultiScale(img, detections, foundWeights);

        float max = 0.0f;
        for (size_t j = 0; j < foundWeights.size(); j++)
        {
            if (foundWeights[j] > max)
                max = foundWeights[j];
        }
        for (size_t j = 0; j < detections.size(); j++)
        {
            if (foundWeights[j] >  max ) //0 //0.1f // max - 0.1f
            {
                Scalar color = Scalar(0, foundWeights[j] * foundWeights[j] * 200, 0);

                rectangle(img, detections[j], color, img.cols / 400 + 1);
            }

        }

        imshow(obj_det_filename, img);

        if (27 == waitKey(delay))
        {
            return 0;
        }
    }
    return 0;
}

int TrainHOGEx::Train(CString csDirPosImgs, CString str_dir, CString csImgPath)
{
    string pos_dir = csDirPosImgs.GetBuffer();
    //string neg_dir = str_dir + "\\N";
    string neg_dir = "D:\\train1\\N";
    String obj_det_filename = str_dir + "\\detector.yml";

    int detector_width = 0;
    int detector_height = 0;



    bool test_detector = false;  
    bool train_twice = true;
    bool visualization = false;



    if (pos_dir.empty() || neg_dir.empty())
    {
        AfxMessageBox("Positive and Negative dir empty.");
    }

    vector< Mat > pos_lst, full_neg_lst, neg_lst, gradient_lst;
    vector< int > labels;

    clog << "Positive images are being loaded...";
    load_images(pos_dir, pos_lst, visualization);

    if (pos_lst.size() > 0)
    {
        clog << "...[done]" << endl;
    }
    else
    {
        clog << "no image in " << pos_dir << endl;
        return 1;
    }

    Size pos_image_size = pos_lst[0].size();

    // get width and height
    Mat img = pos_lst[0];
    detector_width = img.cols;
    detector_height = img.rows;

    Mat imgTarget;
    imgTarget = imread(csImgPath.GetBuffer());

    detector_width = imgTarget.cols;
    detector_height = imgTarget.rows;

    //get trimed width and height  (train function)
    detector_width = detector_width / 8 * 8;
    detector_height = detector_height / 8 * 8;


    if (detector_width && detector_height)
    {
        pos_image_size = Size(detector_width, detector_height);
    }
    else
    {
        //for (size_t i = 0; i < pos_lst.size(); ++i)
        //{
        //  if (pos_lst[i].size() != pos_image_size)
        //  {
        //      cout << "All positive images should be same size!" << endl;
        //      //exit(1);
        //  }
        //}

        pos_image_size = pos_image_size / 8 * 8;

    }


    labels.assign(pos_lst.size(), +1);
    const unsigned int old = (unsigned int)labels.size();

    clog << "Negative images are being loaded...";
    load_images(neg_dir, full_neg_lst, false);
    sample_negex(full_neg_lst, neg_lst, pos_image_size);
    clog << "...[done]" << endl;

    labels.insert(labels.end(), neg_lst.size(), -1);
    CV_Assert(old < labels.size());

    clog << "Histogram of Gradients are being calculated for positive images...";
    computeHOGs(pos_image_size, pos_lst, gradient_lst);
    clog << "...[done]" << endl;

    clog << "Histogram of Gradients are being calculated for negative images...";
    computeHOGs(pos_image_size, neg_lst, gradient_lst);
    clog << "...[done]" << endl;

    Mat train_data;
    convert_to_mlex(gradient_lst, train_data);

    clog << "Training SVM...";
    Ptr< SVM > svm = SVM::create();
    /* Default values to train SVM */
    svm->setCoef0(0.0);
    svm->setDegree(3);
    svm->setTermCriteria(TermCriteria(CV_TERMCRIT_ITER + CV_TERMCRIT_EPS, 1000, 1e-3));
    svm->setGamma(0);
    svm->setKernel(SVM::LINEAR);
    svm->setNu(0.5);
    svm->setP(0.1); // for EPSILON_SVR, epsilon in loss function?
    svm->setC(0.01); // From paper, soft classifier
    svm->setType(SVM::EPS_SVR); // C_SVC; // EPSILON_SVR; // may be also NU_SVR; // do regression task
    svm->train(train_data, ROW_SAMPLE, Mat(labels));
    clog << "...[done]" << endl;


    if (train_twice)
    {
        clog << "Testing trained detector on negative images. This may take a few minutes...";
        HOGDescriptor my_hog;
        my_hog.winSize = pos_image_size;

        // Set the trained svm to my_hog
        vector< float > hog_detector;
        get_svm_detectorex(svm, hog_detector);
        my_hog.setSVMDetector(hog_detector);

        vector< Rect > detections;
        vector< double > foundWeights;

        for (size_t i = 0; i < full_neg_lst.size(); i++)
        {
            my_hog.detectMultiScale(full_neg_lst[i], detections, foundWeights);
            for (size_t j = 0; j < detections.size(); j++)
            {
                Mat detection = full_neg_lst[i](detections[j]).clone();
                resize(detection, detection, pos_image_size);
                neg_lst.push_back(detection);
            }
            if (visualization)
            {
                for (size_t j = 0; j < detections.size(); j++)
                {
                    rectangle(full_neg_lst[i], detections[j], Scalar(0, 255, 0), 2);
                }
                imshow("testing trained detector on negative images", full_neg_lst[i]);
                waitKey(5);
            }
        }
        clog << "...[done]" << endl;

        labels.clear();
        labels.assign(pos_lst.size(), +1);
        labels.insert(labels.end(), neg_lst.size(), -1);

        gradient_lst.clear();
        clog << "Histogram of Gradients are being calculated for positive images...";
        computeHOGs(pos_image_size, pos_lst, gradient_lst);
        clog << "...[done]" << endl;

        clog << "Histogram of Gradients are being calculated for negative images...";
        computeHOGs(pos_image_size, neg_lst, gradient_lst);
        clog << "...[done]" << endl;

        clog << "Training SVM again...";
        convert_to_mlex(gradient_lst, train_data);
        svm->train(train_data, ROW_SAMPLE, Mat(labels));
        clog << "...[done]" << endl;
    }

    vector< float > hog_detector;
    get_svm_detectorex(svm, hog_detector);
    HOGDescriptor hog;
    hog.winSize = pos_image_size;
    hog.setSVMDetector(hog_detector);
    hog.save(obj_det_filename);


    return 0;
}

void TrainHOGEx::ShowImage(CString cs_img)
{
    IplImage * img = 0;

    uchar *data;
    int i, j, k;
    int height, width, widthStep, nChannels;
    img = cvLoadImage(cs_img.GetBuffer(), 3);
    height = img->height;
    width = img->width;
    widthStep = img->widthStep;
    nChannels = img->nChannels;
    data = (uchar*)img->imageData;
    IplImage* img1 = cvCreateImage(cvSize(height / 2, width / 2), IPL_DEPTH_8U, nChannels);
    for (i = 0; i<height / 2; i++) {
        for (j = 0; j<width / 2; j++) {
            for (k = 0; k<3; k++) {
                img1->imageData[i*widthStep + j*nChannels] = data[i*widthStep + j*nChannels];
            }
        }
    }
    cvShowImage("image_Originale2", img1);
    cvWaitKey(0);
    cvReleaseImage(&img);
    return ;

}

int  GetDimension(int& width, int& height)
{
    for (int n = 0; n < 10; n++)
    {
        if (width % 8 != 0)
            width++;
        else
            break;
    }

    for (int n = 0; n < 10; n++)
    {
        if (height % 8 != 0)
            height++;
        else
            break;
    }

    return 0;
}

int TrainHOGEx::CreatePositiveImage(CString cs_imgPath, CString csDirToSave)
{
    bool nagative = false;
    int i = 0;
    char* nullname = (char*)"(NULL)";
    char* vecname = "D:\\1\\appservice.vec"; /* .vec file name */
    char* infoname = NULL; //"D:\\1\\appservice.info"; /* file name with marked up image descriptions */
    char* imagename = cs_imgPath.GetBuffer(); // "D:\\1\\AppService.png"; /* single sample image */
    char* bgfilename = NULL; //"D:\\1\\bg.txt"; /* background */
    int num = 40;
    int bgcolor = 0;
    int bgthreshold = 0; //80
    int invert = 0;
    int maxintensitydev = 40;
    double maxxangle = 0;
    double maxyangle = 0;
    double maxzangle = 0;
    int showsamples = 0;

    /* the samples are adjusted to this scale in the sample preview window */
    Mat img;
    img = imread(imagename);
    double scale = 40.0;

    int width = img.cols; //96; // 83;
    int height = img.rows; // 20;

    int widthOrig = width;
    int heightOrig = height;


    /*int nx = width / 8;
    if (nx*8 < width)
    {
        width = nx * 8 + 16;
    }*/

    for (int n = 0; n < 10; n++)
    {
        if (width % 8 != 0)
            width++;
        else
            break;
    }

    /*int ny = height / 8;
    if (ny * 8 < height)
    {
        height = ny * 8 + 16;
    }*/

    for (int n = 0; n < 10; n++)
    {
        if (height % 8 != 0)
            height++;
        else
            break;
    }

     widthOrig = width;
     heightOrig = height;


    double maxscale = -1;
    if (nagative)
    {
        maxxangle = 20;
        maxyangle = 50;
        maxzangle = 10;
        bgthreshold = 5;
        num = 50;
        invert = true;
        maxintensitydev = 0;
        bgcolor = 50;
    }
    srand((unsigned int)time(0));

    bool b = false;

    /* determine action */
    if (imagename && vecname)
    {
        printf("Create training samples from single image applying distortions...\n");

        cvCreateTrainingSamples(vecname, imagename, bgcolor, bgthreshold, bgfilename,
            num, invert, maxintensitydev,
            maxxangle, maxyangle, maxzangle,
            showsamples, width, height, csDirToSave);



        /*width = widthOrig;
        height = heightOrig;

        width = width * 75 / 100;
        height = height * 75 / 100;

        cvCreateTrainingSamples(vecname, imagename, bgcolor, bgthreshold, bgfilename,
            num, invert, maxintensitydev,
            maxxangle, maxyangle, maxzangle,
            showsamples, width, height, csDirToSave);*/


            /*width = widthOrig;
            height = heightOrig;

            width = width * 125 / 100;
            height = height * 125 / 100;

            GetDimension(width, height);

            cvCreateTrainingSamples(vecname, imagename, bgcolor, bgthreshold, bgfilename,
            num, invert, maxintensitydev,
            maxxangle, maxyangle, maxzangle,
            showsamples, width, height, csDirToSave);*/

        printf("Done\n");
    }
    else if (imagename && bgfilename && infoname)
    {
        printf("Create test samples from single image applying distortions...\n");

        cvCreateTestSamples(infoname, imagename, bgcolor, bgthreshold, bgfilename, num,
            invert, maxintensitydev,
            maxxangle, maxyangle, maxzangle, showsamples, width, height, maxscale);

        printf("Done\n");
    }
    else if (infoname && vecname)
    {
        int total;

        printf("Create training samples from images collection...\n");

        total = cvCreateTrainingSamplesFromInfo(infoname, vecname, num, showsamples,
            width, height);

        printf("Done. Created %d samples\n", total);
    }
    else if (vecname)
    {
        printf("View samples from vec file (press ESC to exit)...\n");

        cvShowVecSamples(vecname, width, height, scale);

        printf("Done\n");
    }
    else
    {
        printf("Nothing to do\n");
    }

    return 0;
}

void TrainHOGEx::Search(CString csDetectorPath, CString test_dir)
{

    CString obj_det_filename;

    obj_det_filename = csDetectorPath + "\\detector.yml";
    test_trained_detector(obj_det_filename.GetBuffer(), test_dir.GetBuffer(), "");
}

VOID TrainHOGEx::TestEx()
{
    mainTestEx();
}

int mainTestEx()
{
    /*
    // Read image
    Mat im = imread("D:\\1\\sa.png");

    // Select ROI
    Rect2d r = selectROI(im);

    // Crop image
    Mat imCrop = im(r);

    // Display Cropped Image
    imshow("Image", imCrop);
    waitKey(0);

    return 0;
    */


    const char* keys =
    {
        "{help h|     | show help message}"
        "{pd    |     | path of directory contains possitive images}"
        "{nd    |     | path of directory contains negative images}"
        "{td    |     | path of directory contains test images}"
        "{tv    |     | test video file name}"
        "{dw    |     | width of the detector}"
        "{dh    |     | height of the detector}"
        "{d     |false| train twice}"
        "{t     |false| test a trained detector}"
        "{v     |false| visualize training steps}"
        "{fn    |my_detector.yml| file name of trained SVM}"
    };


    string pos_dir = "D:\\1\\P";
    string neg_dir = "D:\\1\\N";

    //String pos_dir = parser.get< String >("pd");
    //String neg_dir = parser.get< String >("nd");
    String test_dir = "D:\\1\\P";// parser.get< String >("td");
    String obj_det_filename = "D:\\1\\de.ylm";// parser.get< String >("fn");
    int detector_width = 80;// 83;
    int detector_height = 16;
    bool test_detector = false;  //parser.get< bool >("t");
    bool train_twice = true;// parser.get< bool >("d");
    bool visualization = true;// parser.get< bool >("v");
    string videofilename = "D:\\1\\sa.png";
    if (test_detector)
    {
        test_trained_detector(obj_det_filename, test_dir, videofilename);
        return 0;
    }
    bool testPoc = true;
    if (testPoc)
    {
        detector_width = 96;// 83;
        detector_height = 40;
        pos_dir = "D:\\1\\HOG\\text-pos";
        neg_dir = "D:\\1\\HOG\\eggs-neg";
        obj_det_filename = "D:\\1\\HOG\\build\\Release\\my_text_detector.yml";
        test_dir = "D:\\1\\HOG\\text-test";
        test_trained_detector(obj_det_filename, test_dir, videofilename);
        return 0;
    }

    if (pos_dir.empty() || neg_dir.empty())
    {
    }

    vector< Mat > pos_lst, full_neg_lst, neg_lst, gradient_lst;
    vector< int > labels;

    clog << "Positive images are being loaded...";
    load_images(pos_dir, pos_lst, visualization);

    if (pos_lst.size() > 0)
    {
        clog << "...[done]" << endl;
    }
    else
    {
        clog << "no image in " << pos_dir << endl;
        return 1;
    }

    Size pos_image_size = pos_lst[0].size();

    for (size_t i = 0; i < pos_lst.size(); ++i)
    {
        if (pos_lst[i].size() != pos_image_size)
        {
            cout << "All positive images should be same size!" << endl;
            exit(1);
        }
    }

    pos_image_size = pos_image_size / 8 * 8;

    if (detector_width && detector_height)
    {
        pos_image_size = Size(detector_width, detector_height);
    }

    labels.assign(pos_lst.size(), +1);
    const unsigned int old = (unsigned int)labels.size();

    clog << "Negative images are being loaded...";
    load_images(neg_dir, full_neg_lst, false);
    sample_negex(full_neg_lst, neg_lst, pos_image_size);
    clog << "...[done]" << endl;

    labels.insert(labels.end(), neg_lst.size(), -1);
    CV_Assert(old < labels.size());

    clog << "Histogram of Gradients are being calculated for positive images...";
    computeHOGs(pos_image_size, pos_lst, gradient_lst);
    clog << "...[done]" << endl;

    clog << "Histogram of Gradients are being calculated for negative images...";
    computeHOGs(pos_image_size, neg_lst, gradient_lst);
    clog << "...[done]" << endl;

    Mat train_data;
    convert_to_mlex(gradient_lst, train_data);

    clog << "Training SVM...";
    Ptr< SVM > svm = SVM::create();
    /* Default values to train SVM */
    svm->setCoef0(0.0);
    svm->setDegree(3);
    svm->setTermCriteria(TermCriteria(CV_TERMCRIT_ITER + CV_TERMCRIT_EPS, 1000, 1e-3));
    svm->setGamma(0);
    svm->setKernel(SVM::LINEAR);
    svm->setNu(0.5);
    svm->setP(0.1); // for EPSILON_SVR, epsilon in loss function?
    svm->setC(0.01); // From paper, soft classifier
    svm->setType(SVM::EPS_SVR); // C_SVC; // EPSILON_SVR; // may be also NU_SVR; // do regression task
    svm->train(train_data, ROW_SAMPLE, Mat(labels));
    clog << "...[done]" << endl;

    if (train_twice)
    {
        clog << "Testing trained detector on negative images. This may take a few minutes...";
        HOGDescriptor my_hog;
        my_hog.winSize = pos_image_size;

        // Set the trained svm to my_hog
        vector< float > hog_detector;
        get_svm_detectorex(svm, hog_detector);
        my_hog.setSVMDetector(hog_detector);

        vector< Rect > detections;
        vector< double > foundWeights;

        for (size_t i = 0; i < full_neg_lst.size(); i++)
        {
            my_hog.detectMultiScale(full_neg_lst[i], detections, foundWeights);
            for (size_t j = 0; j < detections.size(); j++)
            {
                Mat detection = full_neg_lst[i](detections[j]).clone();
                resize(detection, detection, pos_image_size);
                neg_lst.push_back(detection);
            }
            if (visualization)
            {
                for (size_t j = 0; j < detections.size(); j++)
                {
                    rectangle(full_neg_lst[i], detections[j], Scalar(0, 255, 0), 2);
                }
                imshow("testing trained detector on negative images", full_neg_lst[i]);
                waitKey(5);
            }
        }
        clog << "...[done]" << endl;

        labels.clear();
        labels.assign(pos_lst.size(), +1);
        labels.insert(labels.end(), neg_lst.size(), -1);

        gradient_lst.clear();
        clog << "Histogram of Gradients are being calculated for positive images...";
        computeHOGs(pos_image_size, pos_lst, gradient_lst);
        clog << "...[done]" << endl;

        clog << "Histogram of Gradients are being calculated for negative images...";
        computeHOGs(pos_image_size, neg_lst, gradient_lst);
        clog << "...[done]" << endl;

        clog << "Training SVM again...";
        convert_to_mlex(gradient_lst, train_data);
        svm->train(train_data, ROW_SAMPLE, Mat(labels));
        clog << "...[done]" << endl;
    }

    vector< float > hog_detector;
    get_svm_detectorex(svm, hog_detector);
    HOGDescriptor hog;
    hog.winSize = pos_image_size;
    hog.setSVMDetector(hog_detector);
    hog.save(obj_det_filename);

    test_trained_detector(obj_det_filename, test_dir, videofilename);

    return 0;
}