Sharpening

Applying the sharpening filter will sharpen the edges in the image. This filter is very useful when we want to enhance the edges in an image that's not crisp. Here are some images to give you an idea of what the image sharpening process looks like:

As you can see in the preceding figure, the level of sharpening depends on the type of kernel we use. We have a lot of freedom to customize the kernel here, and each kernel will give you a different kind of sharpening. To just sharpen an image, like we are doing in the top right image in the preceding picture, we would use a kernel like this:

If we want to do excessive sharpening, like in the bottom left image, we would use the following kernel:

But the problem with these two kernels is that the output image looks artificially enhanced. If we want our images to look more natural, we would use an Edge Enhancement filter. The underlying concept remains the same, but we use an approximate Gaussian kernel to build this filter. It will help us smoothen the image when we enhance the edges, thus making the image look more natural.

Here is the code to achieve the effects applied in the preceding screenshot:

import cv2
import numpy as np

img = cv2.imread('input.jpg')
cv2.imshow('Original', img)

# generating the kernels
kernel_sharpen_1 = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
kernel_sharpen_2 = np.array([[1,1,1], [1,-7,1], [1,1,1]])
kernel_sharpen_3 = np.array([[-1,-1,-1,-1,-1],
                             [-1,2,2,2,-1],
                             [-1,2,8,2,-1],
                             [-1,2,2,2,-1],
                             [-1,-1,-1,-1,-1]]) / 8.0

# applying different kernels to the input image
output_1 = cv2.filter2D(img, -1, kernel_sharpen_1)
output_2 = cv2.filter2D(img, -1, kernel_sharpen_2)
output_3 = cv2.filter2D(img, -1, kernel_sharpen_3)

cv2.imshow('Sharpening', output_1)
cv2.imshow('Excessive Sharpening', output_2)
cv2.imshow('Edge Enhancement', output_3)
cv2.waitKey(0)

If you noticed, in the preceding code, we didn't divide the first two kernels by a normalizing factor. The reason is because the values inside the kernel already sum up to 1, so we are implicitly dividing the matrices by 1.