Histograms of Oriented Gradients 1.0

A mex function for calculating histograms of (oriented) gradients as described in the paper "Histograms of Oriented Gradients for Human Detection"[1]:http://lear.inrialpes.fr/pubs/2005/DT05/Function can be called with either one or two arguments :hogs = HoG(Image,Params);orhogs = HoG(Image);Params should be a size 5 vector with:Params(0) = number of orientation bins.Params(1) = cell size.Params(2) = block size.Params(3) = 1 for oriented gradients and 0 otherwise.Params(4) = value for clipping of the L2-norm.See [1] for more details on these values.If the function is called with only one parameter then the default values are used:Params = [9 8 2 0 0.2];Function can be called for both a RGB and grayscale image.Though the function can be called for uint8 image data, there is a considerable speedup if it is called as HoG(double(Image)).Finally [1] mentions the possibility of downweighting "pixels near the edgesof the block by applying a Gaussian spatial window..." and that this leads to and increase in performance of 1% at 10^-4 FPPW. This downweighting scheme is not used by this function.The HoG function code is part of the MASH public descriptors ("heuristics"):http://mash-project.eu/

Requirements:	No special requirements
Platforms:	Matlab
Keyword:	Considerable,  Finally,  Hogdoubleimage,  Image,  Mentions,  Speedup,  Uint
Users rating:	0/10