如何在灰度图像的python中生成图像在x和y方向的高斯偏导数的联合直方图？

Question

我希望有人能在这个话题上帮助我。因为我想创建一个函数，该函数将灰度图像和箱子数量作为参数，然后计算一阶导数，然后将导数量化为num_bins值的数量，并使用num_bins^2条目数定义2d直方图，并返回hists

任何帮助都将不胜感激！提前谢谢。这就是我所做的

def dxdy_hist(img_gray, num_bins):

    # compute the first derivatives
    # ...
    xderiv = gaussian_filter(img_gray, sigma=(11,0))
    xderiv = gaussian_filter(img_gray, sigma=(0,11))

    # quantize derivatives to "num_bins" number of values
    # ...
    img_gray = img_gray.quantize(num_bins)

    # define a 2D histogram  with "num_bins^2" number of entries
    hists = np.zeros((num_bins, num_bins))

    # ...
    plt.hist2d(xderiv,yderiv,bins=num_bins^2)

    hists = hists.reshape(hists.size)
    return hists