Hello,
I am beginner in computer vision filed;I wanna make project that detect multiple type of objects(e.g. Mug, pen, banana ..)in the same scene so I am planing to use opencv 2.4.6 with c++(is this recommended?),I read about traincascade.exe but actually I don't have the big picture of what is happening, I have Questions:
- what are the algorithms traincascade.exe is used (can I have brief description for each?)I see boost,HoG ,Haar what are these!
- what does it (traincascade.exe) do,what is the input and output for it?
- I have a confusion between terminologies,machine learning,neural network,classifiers and where are those in (traincascade.exe) and opencv generally.
I am sorry if they were dump questions, but I will be happy if any advise me and help me to know.
thanks in advance.