# HOGDescriptor derivAperture parameter

Hi there!

I have search in the OpenCV documentation and I haven't found any clue about derivAperture parameter in the HOGDescriptor function.

Anyone knows what is this parameter for?

edit retag close merge delete

Sort by » oldest newest most voted

Thank you for your answer I will try to discover if it is used for the Sobel operator. It,s defined in this function in objectdetect.cpp

CV_WRAP HOGDescriptor() : winSize(64,128), blockSize(16,16), blockStride(8,8), cellSize(8,8), nbins(9), derivAperture(1), winSigma(-1), histogramNormType(HOGDescriptor::L2Hys), L2HysThreshold(0.2), gammaCorrection(true), nlevels(HOGDescriptor::DEFAULT_NLEVELS)

If anyone had the same problem I think I have found the solution in: http://www.seas.upenn.edu/~bensapp/opencvdocs/ref/opencvref_cv.htm

aperture_size Size of the extended Sobel kernel, must be 1, 3, 5 or 7. In all cases except 1, aperture_size ×aperture_size separable kernel will be used to calculate the derivative. For aperture_size=1 3x1 or 1x3 kernel is used (Gaussian smoothing is not done).

But I'm not totally sure.

more

Hi,

It seems weird but I grepped HOG source code and I'm not able to find a place where this parameter is actually used. I expected it to be aperture size of the Sobel operator to compute derivatives (like Canny has apertureSize parameter). But it seems like this parameter is not used in HOGDescriptor.

more

Official site

GitHub

Wiki

Documentation