Python OpenCV – Canny() Function

In this article, we will see the Canny Edge filter in OpenCV. Canny() Function in OpenCV is used to detect the edges in an image.

Syntax: cv2.Canny(image, T_lower, T_upper, aperture_size, L2Gradient)

Where:

• Image: Input image to which Canny filter will be applied
• T_lower: Lower threshold value in Hysteresis Thresholding
• T_upper: Upper threshold value in Hysteresis Thresholding
• aperture_size: Aperture size of the Sobel filter.
• L2Gradient: Boolean parameter used for more precision in calculating Edge Gradient.

Canny Edge detection is an Algorithm consisting of 4 major steps:

• Reduce Noise using Gaussian Smoothing.
• Compute image gradient using Sobel filter.
• Apply Non-Max Suppression or NMS to just jeep the local maxima
• Finally, apply Hysteresis thresholding which that 2 threshold values T_upper and T_lower which is used in the Canny() function.

Input Image:

Basic example of Canny() function

Python3

import cv2

img = cv2.imread("test.jpeg")  # Read image

# Setting parameter values
t_lower = 50  # Lower Threshold
t_upper = 150  # Upper threshold

# Applying the Canny Edge filter
edge = cv2.Canny(img, t_lower, t_upper)

cv2.imshow('original', img)
cv2.imshow('edge', edge)
cv2.waitKey(0)
cv2.destroyAllWindows()

Output:

Canny() function with Aperture_size

This is an optional parameter that is used to specify the order of the Sobel filter used to calculate the gradient in the Canny algorithm. The default value is 3 and its value should be odd between 3 and 7. You can increase the Aperture size when you want to detect more detailed features.

Python3

import cv2

img = cv2.imread("test.jpeg")  # Read image

# Setting All parameters
t_lower = 100  # Lower Threshold
t_upper = 200  # Upper threshold
aperture_size = 5  # Aperture size

# Applying the Canny Edge filter
# with Custom Aperture Size
edge = cv2.Canny(img, t_lower, t_upper,
                 apertureSize=aperture_size)
cv2.imshow('original', img)
cv2.imshow('edge', edge)
cv2.waitKey(0)
cv2.destroyAllWindows()

Output: 

Canny() function with L2Gradient

It’s a boolean parameter that specifies if you want to calculate the usual gradient equation or the L2Gradient algorithm. Again, it’s an optional parameter. L2gradient is nothing my sqrt(gradient_x_square + gradient_y_square) whereas L1gradient is just abs(gradient_x) + abs(gradient_y).

Python3

import cv2

img = cv2.imread("test.jpeg") # Read image

t_lower = 100 # Lower Threshold
t_upper = 200 # Upper threshold
aperture_size = 5 # Aperture size
L2Gradient = True # Boolean

# Applying the Canny Edge filter with L2Gradient = True
edge = cv2.Canny(img, t_lower, t_upper, L2gradient = L2Gradient )

cv2.imshow('original', img)
cv2.imshow('edge', edge)
cv2.waitKey(0)
cv2.destroyAllWindows()

 Output: 

Canny() function with both Aperture size and L2gradient

Here we will use both attributes within the function.

Python3

import cv2

img = cv2.imread("test.jpeg") # Read image

# Defining all the parameters
t_lower = 100 # Lower Threshold
t_upper = 200 # Upper threshold
aperture_size = 5 # Aperture size
L2Gradient = True # Boolean

# Applying the Canny Edge filter
# with Aperture Size and L2Gradient
edge = cv2.Canny(img, t_lower, t_upper,
                 apertureSize = aperture_size,
                 L2gradient = L2Gradient )

cv2.imshow('original', img)
cv2.imshow('edge', edge)
cv2.waitKey(0)
cv2.destroyAllWindows()

Output: