Sobel and Laplace edge detection in SciPy - Mini Project: Build & Apply

Sobel and Laplace Edge Detection

📖 Scenario: You are working with a simple grayscale image represented as a 2D array. You want to detect edges in this image using two popular methods: Sobel and Laplace filters. These filters help highlight where the image brightness changes sharply, which usually means edges.

🎯 Goal: Build a small program that applies Sobel and Laplace edge detection filters on a given 2D image array and shows the results.

📋 What You'll Learn

Create a 2D numpy array called image with exact pixel values

Create a variable called axis to select the Sobel filter direction

Use scipy.ndimage.sobel to compute the Sobel edges along the chosen axis

Use scipy.ndimage.laplace to compute the Laplace edges

Print the Sobel and Laplace filtered arrays

💡 Why This Matters

🌍 Real World

Edge detection is used in photo editing, computer vision, and robotics to find object boundaries and shapes.

💼 Career

Understanding edge detection is important for roles in image processing, machine learning, and AI development.

1

Create the image array

Create a 2D numpy array called image with these exact values: [[10, 10, 10, 10, 10], [10, 50, 50, 50, 10], [10, 50, 100, 50, 10], [10, 50, 50, 50, 10], [10, 10, 10, 10, 10]]

SciPy

import numpy as np
# Create the 2D numpy array called image with the given values
# Your code here

Need a hint?

Use np.array([...]) to create the 2D array with the exact numbers.

2

Set the Sobel filter axis

Create a variable called axis and set it to 0 to apply the Sobel filter vertically.

SciPy

import numpy as np
image = np.array([[10, 10, 10, 10, 10],
                  [10, 50, 50, 50, 10],
                  [10, 50, 100, 50, 10],
                  [10, 50, 50, 50, 10],
                  [10, 10, 10, 10, 10]])
# Create the variable axis and set it to 0
# Your code here

Need a hint?

Just write axis = 0 to select vertical edges.

3

Apply Sobel and Laplace filters

Import scipy.ndimage and use scipy.ndimage.sobel with image and axis to get sobel_edges. Then use scipy.ndimage.laplace with image to get laplace_edges.

SciPy

import numpy as np
image = np.array([[10, 10, 10, 10, 10],
                  [10, 50, 50, 50, 10],
                  [10, 50, 100, 50, 10],
                  [10, 50, 50, 50, 10],
                  [10, 10, 10, 10, 10]])
axis = 0
# Import scipy.ndimage and apply sobel and laplace filters
# Your code here

Need a hint?

Use scipy.ndimage.sobel(image, axis=axis) and scipy.ndimage.laplace(image).

4

Print the edge detection results

Print the variables sobel_edges and laplace_edges to see the edge detection results.

SciPy

import numpy as np
import scipy.ndimage

image = np.array([[10, 10, 10, 10, 10],
                  [10, 50, 50, 50, 10],
                  [10, 50, 100, 50, 10],
                  [10, 50, 50, 50, 10],
                  [10, 10, 10, 10, 10]])

axis = 0

sobel_edges = scipy.ndimage.sobel(image, axis=axis)
laplace_edges = scipy.ndimage.laplace(image)
# Print sobel_edges and laplace_edges
# Your code here

Need a hint?

Use print(sobel_edges) and print(laplace_edges) to show the results.