Top Hat and Black Hat Transform using Python-OpenCV

In morphology and digital image processing, top-hat and black-hat transform are operations that are used to extract small elements and details from given images. These two types of transforms in which, the top-hat transform is defined as the difference between the input image and its opening by some structuring element, while the black-hat transform is defined as the difference between the closing and the input image. These transforms are used for various image processing tasks, such as feature extraction, background equalization, image enhancement, and others.

Here we will use Opening and Closing morphological operations.

Difference between Top-Hat and Black-Hat

The top-hat filter is used to enhance bright objects of interest in a dark background. The black-hat operation is used to do the opposite, enhance dark objects of interest in a bright background.
Example 1: Top-Hat Transform

Image used:

# Importing OpenCV
import cv2


# Getting the kernel to be used in Top-Hat
filterSize =(3, 3)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,
                                   filterSize)

# Reading the image named 'input.jpg'
input_image = cv2.imread("testing.jpg")
input_image = cv2.cvtColor(input_image, cv2.COLOR_BGR2GRAY)

# Applying the Top-Hat operation
tophat_img = cv2.morphologyEx(input_image,
                              cv2.MORPH_TOPHAT,
                              kernel)

cv2.imshow("original", input_image)
cv2.imshow("tophat", tophat_img)
cv2.waitKey(5000)

Output:

As you can observe in the above image, the very small details are enhanced and taken out using the Top-Hat operation. Hence, it is useful in observing the minor details of the inputs when are present as light pixels on a dark background.

Example 2: Black Hat transform

Input Image:

# Importing OpenCV and numpy
import cv2

# Defining the kernel to be used in Top-Hat
filterSize =(3, 3)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,
                                   filterSize)

# Reading the image named 'input.jpg'
input_image = cv2.imread("testing.jpg")
input_image = cv2.cvtColor(input_image, cv2.COLOR_BGR2GRAY)

# Applying the Black-Hat operation
tophat_img = cv2.morphologyEx(input_image,
                              cv2.MORPH_BLACKHAT,
                              kernel)

cv2.imshow("original", input_image)
cv2.imshow("tophat", tophat_img)
cv2.waitKey(5000)

Output:

Here in this image, all the objects which are white on a dark background are highlighted due to the Black Hat transformation applied to the input image.