skinhat's profile - activity

I am getting big haar training XML files and they arent detecting scissors. Perhaps I need to do without a background like you say. I've done some googling for the term 'inclass variation' but havent found an explaination. Does it mean I shouldnt have too many different types of scissors?

I was wanting to create a Haar trainer for detecting a pair of scissors. I know Haar training is good for detecting faces but is it just as good for objects like scissors or is there something else I should be using other than opencv for detecting every day objects?

Is it possible to convert traincascade-XML into haartraining-XML? I have a java application that uses haartraining-XML (my application doesnt use openCV for detection) therefore I need to use opencv_haartraining.exe to generate cascades but would prefer to use opencv_traincascade.exe because it has lbb and also because seems like opencv_haartraining.exe is going to be phased out.