How to use trainHOG with liblinear or libsvm?
this tutor only for svmlight http://opencv.willowgarage.com/wiki/trainHOG
If you are planning in training with LIBSVM instead of SVMlight, pass me a note so I can provide you with some code.
So where I can find the code?
I'm sorry I do only provide this code on request and I am certainly busy these days, but the code in question is in my opinion not yet clean / bug-free enough to be publicly provided. Besides from the missing time to clean and refactor this code, openCV has deleted my tutorial on how to proceed when training a custom hog detector, so I have to put it up again when I find the time. In the meantime, I added some (unfinished / unclean) code to my github repository found at https://github.com/DaHoC/trainHOG , but please keep in mind that this code is known to contain errors.
Best regards
Thank you for answering the question about "where is the trainHOG tutorial on the openCV site." Given this, is your tutorial available elsewhere?
Kind Regards
The post itself says to contact the following person in order to request for the aditional code:
Jan Hendriks (dahoc3150 [at] yahoo.com)
I guess send him a mail and see if he is willing to help you out?
Also this topic can help you out:
http://answers.opencv.org/question/4351/training-gpu-hogdescriptor-for-multi-scale/
I post request here https://github.com/DaHoC/trainHOG/issues
I wonder why people ignore remarks of the original creator. It clearly states you should mail him for further information :P
Asked: Apr 18 '13
Seen: 3,378 times
Last updated: Sep 26 '13
