Community

Create Positive sample from multiple positive images

I have follow the tutorial Creating your own Haar Cascade OpenCV Python to train my own image classifier.  In the tutorial, only one positive image use to create a positive sample.  The script is

opencv_createsamples -img watch5050.jpg -bg bg.txt -info info/info.lst -pngoutput info -maxxangle 0.5 -maxyangle 0.5 -maxzangle 0.5 -num 1950

.  How I can create a positive sample using multiple positive images?  I have 1000 watches images and 2000 negative images?  Please guide me.  Thank you very much.