python - Patch wise feature vector comparison

Question

I have a image of size of 64*64. I am trying to compute HOG features for the image. I have skimage for my implementation, with the following parameters:

fd1, hog_image = hog(image, orientations=9, pixels_per_cell=(8,8),
                     cells_per_block =(2,2), block_norm = "L2" ,visualize= True)

I get a 36 * 1 dimensional histogram for all 8 * 8 cells with total dimensions = 1764.At the end feature vector is flattened for all histograms. Is there a way that I can find out feature vectors for each 8 * 8 cell?

I would like to compare the feature vector from each 8*8 patch in one image to patch in another image.Something like this.

How do I do that?

标签： pythonimage-processingdistancefeature-extractionhistogram-of-oriented-gradients