如何使用haar训练来检测多个信号?



我正在做一个检测标志的项目,我目前正在使用haar训练来获得手部检测。我培训了不同标志的XML文件。我无法在我的检测程序中使用多个XML文件。无论如何,我可以包括不同的XML文件来检测不同的符号或我可以遵循的另一种方法来检测多个符号

提前感谢。

代码:

if( cascade1)
{
    // There can be more than one hand in an image. So create a growable sequence of hands.
    // Detect the objects and store them in the sequence
    CvSeq* hands1 = cvHaarDetectObjects( img, cascade1, storage,
                                        1.1, 2, CV_HAAR_DO_CANNY_PRUNING,
                                        cvSize(40, 40) );
     // Loop the number of hands found.
    for( i = 0; i < (hands1 ? hands1->total : 0); i++ )
    {
       // Create a new rectangle for drawing the hand
        CvRect* r = (CvRect*)cvGetSeqElem( hands1, i );
        // Find the dimensions of the hand,and scale it if necessary
        pt1.x = r->x*scale;
        pt2.x = (r->x+r->width)*scale;
        pt1.y = r->y*scale;
        pt2.y = (r->y+r->height)*scale;
        // Draw the rectangle in the input image
        cvRectangle( img, pt1, pt2, CV_RGB(230,20,232), 3, 8, 0 );
        //text

          // Show the image in the window named "result"
cvShowImage( "result", img );
}
}
else if (cascade2)
{
    CvSeq* hands2 = cvHaarDetectObjects( img, cascade2, storage,
                                        1.1, 2, CV_HAAR_DO_CANNY_PRUNING,
                                        cvSize(40, 40) );
     // Loop the number of hands found.
    for( i = 0; i < (hands2 ? hands2->total : 0); i++ )
    {
       // Create a new rectangle for drawing the hand
        CvRect* r = (CvRect*)cvGetSeqElem( hands2, i );
        // Find the dimensions of the hand,and scale it if necessary
        pt3.x = r->x*scale;
        pt4.x = (r->x+r->width)*scale;
        pt3.y = r->y*scale;
        pt4.y = (r->y+r->height)*scale;
        // Draw the rectangle in the input image
        cvRectangle( img, pt3, pt4, CV_RGB(230,20,232), 3, 8, 0 );
        //text

         // Show the image in the window named "result"
cvShowImage( "result", img );

只检测onexml文件

最简单的方法是逐个用不同的XML文件检测符号,然后将结果合并。

相关内容

  • 没有找到相关文章

最新更新