No account yet ?
Tested in Anaconda and Python 3.7
import numpy as np from skimage.io import imread from skimage.color import rgb2gray import matplotlib.pyplot as plt input_pixels = np.array(rgb2gray(imread('resources/city.jpg'))*256, dtype=np.uint8) plt.axis("off") plt.imshow(input_pixels, cmap="gray") kernel_horizontal = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]], dtype = np.float) kernel_vertical = np.array([[1, 2, 1], [0, 0, 0], [-1, -2, -1]], dtype = np.float) from scipy import signal Gx = signal.convolve2d(input_pixels, kernel_horizontal, boundary='symm', mode='same') Gy = signal.convolve2d(input_pixels, kernel_vertical, boundary='symm', mode='same') gradient_magnitude = np.sqrt(Gx * Gx + Gy * Gy) gradient_magnitude *= 255.0 / np.max(gradient_magnitude) plt.imshow(gradient_magnitude, cmap="gray")
ml_research - GitHub
Original image
Grayscale
Gx
Gy
Sobel filter
Welcome, my name is Eric Soupet and I am the administrator of the site elodees.com. elodees.com is a state of the art of Artificial Intelligence and aims to be collaborative, you can now offer content such as articles, events, tutorials, ... so don't hesitate !
Platform images credit : Pixabay - Pixabay License | Pexels - Pexels License