Revision history [back]

Dears,

I'm trying to understand HOG descriptor which I am using e.g.

//extraction of HoG feature
HOGDescriptor hog(Size(32, 16), Size(4, 4), Size(8, 8), Size(4, 4), 9);
// Size(32,16), //winSize
// Size(8,8), //blocksize
// Size(4,4), //blockStride,
// Size(4,4), //cellSize,
// 9, //nbins,

hog.compute(img1_gray, descriptorsValues1, Size(0, 0), Size(0, 0), locations1);

I have example from scikit-image http://scikit-image.org/docs/dev/auto_examples/features_detection/plot_hog.html

fd, hog_image = hog(image, orientations=8, pixels_per_cell=(16, 16),
                    cells_per_block=(1, 1), visualize=True)

I wanna undestand params of OpenCV HOGDescriptor and translate hog params from scikit-image hog to opencv

What winSize, blocksize, blockStride, cellSize and nbins mean of HOGDescriptor?

What descriptors, winStride, padding, locations of hog.compute() mean?

Thank you.