if I have an image with 11x11 pixels and In the center of the image is a square of 5x5 pixels. The gray level of the background is 0 and the gray level of the square is 50. How can I compute the result of the magnitude of edges given by the compass operator for this image taking into account that the image is not noisy? I have the code but I don't know how to apply the math on paper...
from skimage import filters
import numpy as np
grad_x = filters.sobel_h(input_image)
grad_y = filters.sobel_v(input_image)
edge_magnitude = np.sqrt(grad_x**2+grad_y**2)