Is it possible to combine different features in a classification task? I read about training SVMs for each kind of collected descriptors and then use a weighted summation of the results to actually integrate/combine information, but how it should be done in practice?.
Hello there,
I am applying the same approach for my phd study, combining more information channels to actually get more accurate detection/classification of a segmented region. For this I have based myself on the work of Piotr Dollár. Check out his paper, it suggests an approach for better classifying of pedestrians through the use of color spaces where the head region is actually more clear.
Link to paper: http://vision.ucsd.edu/~pdollar/files/papers/DollarBMVC09ChnFtrs.pdf
I am still processing some basic steps in Matlab and am planning to implement this approach in OpenCV. However it can already give you an idea of the possibilities.
Cheers!
Asked: Feb 27 '13
Seen: 420 times
Last updated: Feb 27 '13
