smiledetect.cpp 8.69 KB
Newer Older
wester committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247
#include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"

#include <cctype>
#include <iostream>
#include <iterator>
#include <stdio.h>

using namespace std;
using namespace cv;

static void help()
{
    cout << "\nThis program demonstrates the smile detector.\n"
            "Usage:\n"
            "./smiledetect [--cascade=<cascade_path> this is the frontal face classifier]\n"
            "   [--smile-cascade=[<smile_cascade_path>]]\n"
            "   [--scale=<image scale greater or equal to 1, try 2.0 for example. The larger the faster the processing>]\n"
            "   [--try-flip]\n"
            "   [video_filename|camera_index]\n\n"
            "Example:\n"
            "./smiledetect --cascade=\"../../data/haarcascades/haarcascade_frontalface_alt.xml\" --smile-cascade=\"../../data/haarcascades/haarcascade_smile.xml\" --scale=2.0\n\n"
            "During execution:\n\tHit any key to quit.\n"
            "\tUsing OpenCV version " << CV_VERSION << "\n" << endl;
}

void detectAndDraw( Mat& img, CascadeClassifier& cascade,
                    CascadeClassifier& nestedCascade,
                    double scale, bool tryflip );

string cascadeName = "../../data/haarcascades/haarcascade_frontalface_alt.xml";
string nestedCascadeName = "../../data/haarcascades/haarcascade_smile.xml";


int main( int argc, const char** argv )
{
    CvCapture* capture = 0;
    Mat frame, frameCopy, image;
    const string scaleOpt = "--scale=";
    size_t scaleOptLen = scaleOpt.length();
    const string cascadeOpt = "--cascade=";
    size_t cascadeOptLen = cascadeOpt.length();
    const string nestedCascadeOpt = "--smile-cascade";
    size_t nestedCascadeOptLen = nestedCascadeOpt.length();
    const string tryFlipOpt = "--try-flip";
    size_t tryFlipOptLen = tryFlipOpt.length();
    string inputName;
    bool tryflip = false;

    help();

    CascadeClassifier cascade, nestedCascade;
    double scale = 1;

    for( int i = 1; i < argc; i++ )
    {
        cout << "Processing " << i << " " <<  argv[i] << endl;
        if( cascadeOpt.compare( 0, cascadeOptLen, argv[i], cascadeOptLen ) == 0 )
        {
            cascadeName.assign( argv[i] + cascadeOptLen );
            cout << "  from which we have cascadeName= " << cascadeName << endl;
        }
        else if( nestedCascadeOpt.compare( 0, nestedCascadeOptLen, argv[i], nestedCascadeOptLen ) == 0 )
        {
            if( argv[i][nestedCascadeOpt.length()] == '=' )
                nestedCascadeName.assign( argv[i] + nestedCascadeOpt.length() + 1 );
        }
        else if( scaleOpt.compare( 0, scaleOptLen, argv[i], scaleOptLen ) == 0 )
        {
            if( !sscanf( argv[i] + scaleOpt.length(), "%lf", &scale ) || scale < 1 )
                scale = 1;
            cout << " from which we read scale = " << scale << endl;
        }
        else if( tryFlipOpt.compare( 0, tryFlipOptLen, argv[i], tryFlipOptLen ) == 0 )
        {
            tryflip = true;
            cout << " will try to flip image horizontally to detect assymetric objects\n";
        }
        else if( argv[i][0] == '-' )
        {
            cerr << "WARNING: Unknown option " << argv[i] << endl;
        }
        else
            inputName.assign( argv[i] );
    }

    if( !cascade.load( cascadeName ) )
    {
        cerr << "ERROR: Could not load face cascade" << endl;
        help();
        return -1;
    }
    if( !nestedCascade.load( nestedCascadeName ) )
    {
        cerr << "ERROR: Could not load smile cascade" << endl;
        help();
        return -1;
    }

    if( inputName.empty() || (isdigit(inputName.c_str()[0]) && inputName.c_str()[1] == '\0') )
    {
        capture = cvCaptureFromCAM( inputName.empty() ? 0 : inputName.c_str()[0] - '0' );
        int c = inputName.empty() ? 0 : inputName.c_str()[0] - '0' ;
        if(!capture) cout << "Capture from CAM " <<  c << " didn't work" << endl;
    }
    else if( inputName.size() )
    {
        capture = cvCaptureFromAVI( inputName.c_str() );
        if(!capture) cout << "Capture from AVI didn't work" << endl;
    }

    cvNamedWindow( "result", 1 );

    if( capture )
    {
        cout << "In capture ..." << endl;
        cout << endl << "NOTE: Smile intensity will only be valid after a first smile has been detected" << endl;

        for(;;)
        {
            IplImage* iplImg = cvQueryFrame( capture );
            frame = iplImg;
            if( frame.empty() )
                break;
            if( iplImg->origin == IPL_ORIGIN_TL )
                frame.copyTo( frameCopy );
            else
                flip( frame, frameCopy, 0 );

            detectAndDraw( frameCopy, cascade, nestedCascade, scale, tryflip );

            if( waitKey( 10 ) >= 0 )
                goto _cleanup_;
        }

        waitKey(0);

_cleanup_:
        cvReleaseCapture( &capture );
    }
    else
    {
        cerr << "ERROR: Could not initiate capture" << endl;
        help();
        return -1;
    }

    cvDestroyWindow("result");
    return 0;
}

void detectAndDraw( Mat& img, CascadeClassifier& cascade,
                    CascadeClassifier& nestedCascade,
                    double scale, bool tryflip)
{
    int i = 0;
    vector<Rect> faces, faces2;
    const static Scalar colors[] =  { CV_RGB(0,0,255),
        CV_RGB(0,128,255),
        CV_RGB(0,255,255),
        CV_RGB(0,255,0),
        CV_RGB(255,128,0),
        CV_RGB(255,255,0),
        CV_RGB(255,0,0),
        CV_RGB(255,0,255)} ;
    Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );

    cvtColor( img, gray, CV_BGR2GRAY );
    resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
    equalizeHist( smallImg, smallImg );

    cascade.detectMultiScale( smallImg, faces,
        1.1, 2, 0
        //|CV_HAAR_FIND_BIGGEST_OBJECT
        //|CV_HAAR_DO_ROUGH_SEARCH
        |CV_HAAR_SCALE_IMAGE
        ,
        Size(30, 30) );
    if( tryflip )
    {
        flip(smallImg, smallImg, 1);
        cascade.detectMultiScale( smallImg, faces2,
                                 1.1, 2, 0
                                 //|CV_HAAR_FIND_BIGGEST_OBJECT
                                 //|CV_HAAR_DO_ROUGH_SEARCH
                                 |CV_HAAR_SCALE_IMAGE
                                 ,
                                 Size(30, 30) );
        for( vector<Rect>::const_iterator r = faces2.begin(); r != faces2.end(); r++ )
        {
            faces.push_back(Rect(smallImg.cols - r->x - r->width, r->y, r->width, r->height));
        }
    }

    for( vector<Rect>::iterator r = faces.begin(); r != faces.end(); r++, i++ )
    {
        Mat smallImgROI;
        vector<Rect> nestedObjects;
        Point center;
        Scalar color = colors[i%8];
        int radius;

        double aspect_ratio = (double)r->width/r->height;
        if( 0.75 < aspect_ratio && aspect_ratio < 1.3 )
        {
            center.x = cvRound((r->x + r->width*0.5)*scale);
            center.y = cvRound((r->y + r->height*0.5)*scale);
            radius = cvRound((r->width + r->height)*0.25*scale);
            circle( img, center, radius, color, 3, 8, 0 );
        }
        else
            rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
                       cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
                       color, 3, 8, 0);

        const int half_height=cvRound((float)r->height/2);
        r->y=r->y + half_height;
        r->height = half_height;
        smallImgROI = smallImg(*r);
        nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
            1.1, 0, 0
            //|CV_HAAR_FIND_BIGGEST_OBJECT
            //|CV_HAAR_DO_ROUGH_SEARCH
            //|CV_HAAR_DO_CANNY_PRUNING
            |CV_HAAR_SCALE_IMAGE
            ,
            Size(30, 30) );

        // The number of detected neighbors depends on image size (and also illumination, etc.). The
        // following steps use a floating minimum and maximum of neighbors. Intensity thus estimated will be
        //accurate only after a first smile has been displayed by the user.
        const int smile_neighbors = (int)nestedObjects.size();
        static int max_neighbors=-1;
        static int min_neighbors=-1;
        if (min_neighbors == -1) min_neighbors = smile_neighbors;
        max_neighbors = MAX(max_neighbors, smile_neighbors);

        // Draw rectangle on the left side of the image reflecting smile intensity
        float intensityZeroOne = ((float)smile_neighbors - min_neighbors) / (max_neighbors - min_neighbors + 1);
        int rect_height = cvRound((float)img.rows * intensityZeroOne);
        CvScalar col = CV_RGB((float)255 * intensityZeroOne, 0, 0);
        rectangle(img, cvPoint(0, img.rows), cvPoint(img.cols/10, img.rows - rect_height), col, -1);
    }

    cv::imshow( "result", img );
}