Scikit Image - Image Inversion

Quiz

Image inversion, also known as image negation or image complement, refers to the process of reversing the intensity values of an image. Inverting an image results in a new image where the brightest pixels become the darkest and vice versa.

The process of inverting an image varies depending on the type of image data.

Binary Images: inversion changes True values to False and vice versa.
Grayscale Images: For grayscale images, each pixel value is replaced by the difference between the maximum value allowed by the data type (for example, 255 for 8-bit images) and the original pixel value. This will flip the brightness levels, making dark areas appear bright and vice versa.
RGB Images: In the case of color images represented as RGB (Red, Green, Blue) channels, the inversion operation is applied independently to each channel. Each channel is inverted following the same approach as grayscale images.

To perform image inversion using the scikit-image library, you can use the invert() function from the util submodule of the scikit-image library.

Inverting an image using Scikit Image

The skimage.util.invert() method is used to reverse the intensity range of an input image. The maximum value of the data type becomes the minimum, and vice versa. The behavior of this operation varies depending on the data type of the input:

For unsigned integers, the image is subtracted from the maximum value of the data type.
For signed integers, the image is subtracted from -1. This approach is used because the range of signed integers is asymmetric. For example, if the input image is of type np.int8 (range [-128, 127]), by multiplying the image by -1, the maximum value would become 128 which is outside the valid range. By subtracting from -1, the maximum value 128 correctly maps to the value 127.
For floating-point numbers, if the 'signed_float' parameter is set to False (assuming the image is unsigned), the image is subtracted from 1. If 'signed_float' is set to True, the subtraction is performed with 0.

Syntax

Following is the syntax of this method −

skimage.util.invert(image, signed_float=False)

Parameters

image: The input image in CIE-Luv color space. The shape of the array should be at least 2-D with the last dimension having a size of 3, representing the CIE-Luv channels.
signed_float (optional): A boolean flag. When True and the image is of type float, the range is assumed to be [-1, 1]. When False and the image is of type float, the range is assumed to be [0, 1].

Return Value

This method returns the inverted image as an ndarray.

Example

The following example, the original binary image is inverted using the util.invert() function.

import numpy as np
from skimage import util, io
import matplotlib.pyplot as plt

# Create a binary image
binary_image = np.array([[False, True, False],
                         [True, False, True],
                         [False, True, False]])

# Invert the binary image
inverted_binary_image = util.invert(binary_image)

# Display the input and output images using Matplotlib
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(10, 5))
 
axes[0].imshow(binary_image)
axes[0].set_title('Input Binary Image')
axes[0].axis('off')
 
axes[1].imshow(inverted_binary_image)
axes[1].set_title('Output Inverted Binary Image')
axes[1].axis('off')

plt.tight_layout()
plt.show()

Output

When you run the above program, it will generate the following output −

Example

The following example does the grayscale image inversion using the util.invert() function.

import numpy as np
from skimage import io, util
import matplotlib.pyplot as plt
 
# Read an image
image = io.imread('Images/Tajmahal.jpg', as_gray=True)

# Invert the Gray scale image
inverted_gray_image = util.invert(image)

# Display the input and output images using Matplotlib
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(10, 5))
 
axes[0].imshow(image)
axes[0].set_title('Input Gray Image')
axes[0].axis('off')
 
axes[1].imshow(inverted_gray_image)
axes[1].set_title('Output Inverted Gray Image')
axes[1].axis('off')

plt.tight_layout()
plt.show()

Output

On executing the above program, you will get the following output.

Example

In the following example, the original RGB image will be inverted using the util.invert() function.

import numpy as np
from skimage import io, util
import matplotlib.pyplot as plt
 
# Read an image
image = io.imread('Images/Tajmahal.jpg')

# Invert the RGB image
inverted_rgb_image = util.invert(image)

# Display the input and output images using Matplotlib
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(10, 5))
 
axes[0].imshow(image)
axes[0].set_title('Input RGB Image')
axes[0].axis('off')
 
axes[1].imshow(inverted_rgb_image)
axes[1].set_title('Output Inverted RGB Image')
axes[1].axis('off')

plt.tight_layout()
plt.show()

Output

On executing the above program, you will get the following output.

Print Page