Edge detection using Canny algorithm in python
3 min read

Edge detection using Canny algorithm in python

Edge detection using Canny algorithm in python

what is edge detection?

Edge detection is an image processing technique for finding the boundaries of objects within images. It works by detecting discontinuities in brightness.

where edge detection is used?

Edge detection is used for image segmentation and data extraction in areas such as image processing, computer vision, and* machine vision*, so knowing how to do it will eventually pay you off.


There are several edge detection algorithms and different libraries supporting it but in this tutorial, I'm going to show you how to do it using OpenCV using the Canny algorithm.


Installation in  window

For window just use normal pip to install the dependencies  just as shown below;

pip install opencv-python

pip install matplotlib

Installation on Linux

For Linux, you might need to use pip3 to specify that you're installing the dependencies on python3.

pip3 install opencv-python

pip3 install matplotlib

Let's get started

Once we have installed now we ready to go to detecting edges with python using Canny algorithms.

we are going to use the OpenCV method imread() to load an image from the file, use *Canny() *to detect the edges, and then finally visualizing the images before detection and after using Matplotlib

Reading images with OpenCV

To read an image from a file using the imread() method you need to provide two-parameter, one is for the path to our raw image, and the next one is a mode of reading which can either by GRAY, RGB, HSV, HSL, and etc.

OpenCV syntax to read image

import cv2​

image = cv2.imread(path_to_image, mode_of_reading)

Canny algorithms usually work well when the image is in grayscale, there is a shortcut in OpenCV to open an image in a grayscale mode which is done by putting 0 on the mode of reading.

Using Canny algorithms to detect the edges

To detect edges with Canny you have to specify your raw image, lower pixel threshold, and higher pixel threshold in the order shown below;

image_with_edges = cv2.Canny(raw_image, l_threshold, h_theshold)

How threshold affect edge detection?

The intensity gradient of a pixel is greater than the higher threshold, it will be added as an edge pixel in the output image otherwise it will be rejected completely.

Finalizing our code and Visualizing it with Matplotlib

Now that's we learned the basics of OpenCV together with Canny detection algorithms now let's put them together to sample real-world application

Let's detect the edges in the below sample case image road.jpg

Alt Text

Using the knowledge we just learned above, I have bundled everything together to come up with below final code below, when you run it, it will load an image, perform detection and display it using Matplotlib.

import cv2
import matplotlib.pyplot as plt 

def detect_edge(image):
    ''' function Detecting Edges '''
    image_with_edges = cv2.Canny(image , 100, 200)
    images = [image , image_with_edges]
    location = [121, 122]
    for loc, img in zip(location, images):
        plt.imshow(img, cmap='gray')
image = cv2.imread('road.jpg', 0)


Once executed it will render a picture with edges just as shown in the picture below;

Congratulations you have just learned how to detect edges in python, you should be proud of yourself, Also in case of anything, drop it in the comment box below and I will get back to you ASAP