Image enhancement

Image enhancement is the process of improving the quality and

appearance of an image. It can be used to correct flaws or defects
in an image, or to simply make an image more visually appealing.
Image enhancement techniques can be applied to a wide range of
images, including photographs, scans, and digital images. Some
common goals of image enhancement include increasing contrast,
sharpness, and colorfulness; reducing noise and blur; and
correcting distortion and other defects. Image enhancement
techniques can be applied manually using image editing software,
or automatically using algorithms and computer programs such as
OpenCV.
In this article, we will explore a variety of image enhancement
techniques that can be performed using OpenCV and Python.
OpenCV is a powerful, open-source computer vision library that
provides a wide range of image processing and computer vision
algorithms. By combining the capabilities of OpenCV with the
versatility of Python, we can easily implement a variety of image
enhancement techniques to improve the quality and appearance of
our images.
In the following sections, we will discuss the different image
enhancement techniques and how to implement them using
OpenCV and Python. There are several image enhancement
techniques that you can use with OpenCV and Python to improve
the quality and clarity of images. Here are a few examples:

Adjusting brightness and contrast

Adjusting the brightness and contrast of an image can significantly

affect its visual appeal and effectiveness. It can also help to correct
defects or flaws in the image and make it easier to see details.
Finding the right balance of brightness and contrast is important for
creating an attractive and effective image.
There are several ways to adjust the brightness and contrast of an
image using OpenCV and Python. One common method is to use
the cv2.addWeighted() function, which allows you to adjust the
brightness by adding a scalar value to each pixel in the image, and
the contrast by scaling the pixel values.
Here is an example of how to adjust the brightness and contrast of
an image using the cv2.addWeighted() function:

Python3
#Import the necessary libraries
 import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Adjust the brightness and contrast

# Adjusts the brightness by adding 10 to each pixel value
brightness = 10
# Adjusts the contrast by scaling the pixel values by 2.3
contrast = 2.3
image2 = cv2.addWeighted(image, contrast,
np.zeros(image.shape, image.dtype), 0, brightness)

#Save the image

cv2.imwrite('modified_image.jpg', image2)
#Plot the contrast image
plt.subplot(1, 2, 2)
plt.title("Brightness & contrast")
plt.imshow(image2)
plt.show()

Output:

Brightness & contrast

In this example, the brightness of the image is adjusted by adding

10 to each pixel value, and the contrast is adjusted by scaling the
pixel values by 2.3. You can adjust the values of brightness and
contrast to achieve the desired level of brightness and contrast.
Another method for adjusting the brightness and contrast of an
image is to use the cv2.convertScaleAbs() function, which allows
you to adjust the brightness and contrast using a combination of
scaling and shifting the pixel values.

Python3
#Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Adjust the brightness and contrast

# g(i,j)=α⋅f(i,j)+β
# control Contrast by 1.5
alpha = 1.5
# control brightness by 50
beta = 50
image2 = cv2.convertScaleAbs(image, alpha=alpha, beta=beta)

#Save the image

cv2.imwrite('Brightness & contrast.jpg', image2)
#Plot the contrast image
plt.subplot(1, 2, 2)
plt.title("Brightness & contrast")
plt.imshow(image2)
plt.show()

Outputs:
 Brightness & contrast

In this example, the brightness and contrast are adjusted using a

combination of scaling and shifting the pixel values. You can adjust
the values of alpha and beta to achieve the desired level of
brightness and contrast.

Sharpening images

Sharpening is the process of enhancing the edges and fine details

in an image to make it appear sharper and more defined. It is
important because it can help to bring out the details and features
in an image, making it more visually appealing and easier to
understand. Sharpening can be used to correct blur or softness in
an image and can be applied using a variety of techniques.
One common method for sharpening images using OpenCV and
Python is to use the cv2.filter2D() function, which convolves the
image with a kernel. The kernel can be designed to enhance the
edges in the image, resulting in a sharper image.
Here is an example of how to sharpen an image using the
cv2.filter2D() function:

Python3
#Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

 plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Create the sharpening kernel

kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]])

# Sharpen the image

sharpened_image = cv2.filter2D(image, -1, kernel)

#Save the image

cv2.imwrite('sharpened_image.jpg', sharpened_image)

#Plot the sharpened image

plt.subplot(1, 2, 2)
plt.title("Sharpening")
plt.imshow(sharpened_image)
plt.show()

Output:

Sharpening

In this example, a 3×3 sharpening kernel is used to enhance the

edges in the image. You can experiment with different kernels to
achieve the desired level of sharpening. Numpy is used to create
the sharpening kernel is created as a NumPy array using the
np.array() function. This array is then passed as an argument to the
cv2.filter2D() function, which convolves the image with the kernel
to sharpen it.
Another method for sharpening images is to use the cv2.Laplacian()
function, which calculates the Laplacian of an image and returns
the result as a sharpened image.

Python3
 #Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Sharpen the image using the Laplacian operator

sharpened_image2 = cv2.Laplacian(image, cv2.CV_64F)

#Save the image

cv2.imwrite('Laplacian sharpened_image.jpg',
sharpened_image2)

#Plot the sharpened image

plt.subplot(1, 2, 2)
plt.title("Laplacian Sharpening")
plt.imshow(sharpened_image2)
plt.show()

Output:

Laplacian Sharpening

In this example, the Laplacian operator calculates the sharpened

image. You can adjust the depth of the output image using the
cv2.CV_64F parameter.

Removing noise from images

Noise reduction is the process of removing or reducing unwanted
noise or artifacts from an image. It is important because it can
improve the visual quality and clarity of the image and make it
easier to analyze or process using computer algorithms. Noise can
be introduced into an image due to a variety of factors and can
degrade its quality. There are several techniques for reducing
noise, including using filters such as the median filter or the
Gaussian filter. It is important to apply noise reduction judiciously
to avoid blur or loss of detail in the image.
One common method for removing noise from images using
OpenCV and Python is to use a median filter. The median filter
works by replacing each pixel in the image with the median value
of a set of neighboring pixels. This can help to smooth out noise
and reduce artifacts in the image.
Here is an example of how to remove noise from an image using
the cv2.medianBlur() function in OpenCV:

Python3
#Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Remove noise using a median filter

filtered_image = cv2.medianBlur(image, 11)

#Save the image

cv2.imwrite('Median Blur.jpg', filtered_image)

#Plot the blured image

plt.subplot(1, 2, 2)
plt.title("Median Blur")
plt.imshow(filtered_image)
plt.show()

Output:
 Median Blur

In this example, the cv2.medianBlur() function is used to apply a

median filter to the image. The 5 parameter specifies the size of
the kernel to use for the filter. You can adjust the kernel size to
achieve the desired level of noise reduction.
Another method for removing noise from images is to use a
Gaussian filter, which uses a weighted average of neighboring
pixels to smooth out noise and reduce artifacts. You can use the
cv2.GaussianBlur() function to apply a Gaussian filter to an image
in OpenCV.

Python3
#Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Remove noise using a Gaussian filter

filtered_image2 = cv2.GaussianBlur(image, (7, 7), 0)

#Save the image

cv2.imwrite('Gaussian Blur.jpg', filtered_image2)

#Plot the blured image

plt.subplot(1, 2, 2)
 plt.title("Gaussian Blur")
plt.imshow(filtered_image2)
plt.show()

Output:

Gaussian Blur

In this example, the cv2.GaussianBlur() function is used to apply a

Gaussian filter to the image. The (5, 5) parameter specifies the size
of the kernel to use for the filter, and the 0 parameter specifies the
standard deviation of the Gaussian function. You can adjust these
parameters to achieve the desired level of noise reduction.

Enhancing color in images

Color enhancement is adjusting the colors in an image to make

them more vibrant, balanced, or natural. It can be used to correct
color defects or problems in an image or to simply make an image
more appealing and aesthetically pleasing. Color enhancement is
important because it can significantly affect the visual impact and
effectiveness of an image. It can also be useful for correcting color
errors or problems in an image and can make it easier to see
details and features in the image. There are several techniques for
enhancing the colors in an image, including adjusting the color
balance, adjusting the saturation, and adjusting the hue.
There are several ways to enhance the colors in an image using
OpenCV and Python. One common method is to use the
cv2.cvtColor() function, which allows you to convert the image from
one color space to another. This can be useful for adjusting the
color balance or saturation of the image.
Here is an example of how to enhance the colors in an image using
the cv2.cvtColor() function:

Python3
#Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Convert the image from BGR to HSV color space

image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)

# Adjust the hue, saturation, and value of the image

# Adjusts the hue by multiplying it by 0.7
image[:, :, 0] = image[:, :, 0] * 0.7
# Adjusts the saturation by multiplying it by 1.5
image[:, :, 1] = image[:, :, 1] * 1.5
# Adjusts the value by multiplying it by 0.5
image[:, :, 2] = image[:, :, 2] * 0.5

# Convert the image back to BGR color space

image2 = cv2.cvtColor(image, cv2.COLOR_HSV2BGR)

#Save the image

cv2.imwrite('enhanced coloured.jpg', image2)

#Plot the enhanced image

plt.subplot(1, 2, 2)
plt.title("enhanced coloured")
plt.imshow(image2)
plt.show()

Output:
 Enhanced Coloured

This code first converts the image from the BGR color space to the
HSV color space using the cv2.cvtColor() function. It then adjusts
the hue, saturation, and value (brightness) of the image by
multiplying the corresponding channels by a scalar value. Finally, it
converts the image back to the BGR color space and saves the
modified image. You can adjust the scalar values to achieve the
desired level of color enhancement.

Image resizing and scaling

Image resizing and scaling involve adjusting the dimensions and

size of an image. Both are important for meeting specific
requirements or context, such as fitting a specific size or aspect
ratio or reducing the file size. There are several techniques,
including interpolation methods like the nearest neighbor, bilinear,
and bicubic interpolation. It is important to choose a method that
preserves image quality and clarity.
You can use the cv2.resize() function in OpenCV to resize and scale
images. The cv2.resize() function takes the following arguments:
 src: The input image.
 dsize: The size of the output image, specified as a tuple
(width, height).
 fx: The scaling factor along the x-axis.
 fy: The scaling factor along the y-axis.
 interpolation: The interpolation method to use.
Here is an example of how to use the cv2.resize() function to resize
an image:

Python3
#Import the necessary libraries
 import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Resize the image to a specific width and height

resized_image = cv2.resize(image, (2100, 1500))

#Save the Resized image

cv2.imwrite('Resized image.jpg', resized_image)

#Plot the Resized image

plt.subplot(1, 2, 2)
plt.title("Resized")
plt.imshow(resized_image)
plt.show()

Output:

Resized Image

In this example, the image is resized to a width of 400 pixels and a

height of 300 pixels.
You can also use the fx and fy parameters to specify the scaling
factors along the x-axis and y-axis, respectively. For example:

Python3
#Import the necessary libraries
 import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Scale the image by a factor of 2 along both axes

scaled_image = cv2.resize(image, None, fx=2, fy=2)

#Save the image

cv2.imwrite('Scaled.jpg', scaled_image)

#Plot the Scaled image

plt.subplot(1, 2, 2)
plt.title("Scaled")
plt.imshow(scaled_image)
plt.show()

Output:

Scaled Image

In this example, the image is scaled by a factor of 2 along both

axes, resulting in an image that is twice the size of the original. The
interpolation parameter allows you to specify the interpolation
method to use when resizing or scaling the image. The available
options include cv2.INTER_NEAREST, cv2.INTER_LINEAR,
cv2.INTER_CUBIC, and others.
This is just a basic example of how to resize and scale images using
OpenCV and Python. You can adjust the size and scaling factors to
achieve the desired results, and you can also specify the
interpolation method to use when resizing or scaling the image.

Inverse Transform

We can also inverse the color by simply subtracting each value

from 255

Python3
#Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Inverse by subtracting from 255

inverse_image = 255 - image

#Save the image

cv2.imwrite('inverse_image.jpg', inverse_image)
#Plot the Inverse image
plt.subplot(1, 2, 2)
plt.title("Inverse color")
plt.imshow(inverse_image)
plt.show()

Output:
 Inverse color

Equalizing histograms –

Histogram equalization is a technique used to adjust the contrast of

an image by spreading out the intensity values of the pixels in the
image. It is important because it can improve the contrast and
clarity of an image, making it easier to see details and features that
might be difficult to see in an image with low contrast. There are
several different methods for performing histogram equalization,
including global histogram equalization and local histogram
equalization. Global histogram equalization adjusts the contrast of
the entire image, while local histogram equalization adjusts the
contrast in small, localized areas of the image.
You can use the cv2.equalizeHist() function in OpenCV to equalize
the histogram of an image. This function takes the image data as
an argument and returns the equalized image data. Here is an
example of how to use the cv2.equalizeHist() function to equalize
the histogram of an image:

Python3
#Import the necessary libraries
import cv2
import matplotlib.pyplot as plt
import numpy as np

# Load the image

image = cv2.imread('GFG.jpeg')

#Plot the original image

plt.subplot(1, 2, 1)
plt.title("Original")
plt.imshow(image)

# Convert the image to grayscale

gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# Equalize the histogram

equalized_image = cv2.equalizeHist(gray_image)

#Save the equalized image

cv2.imwrite('equalized.jpg', equalized_image)

#Plot the equalized image

plt.subplot(1, 2, 2)
 plt.title("equalized")
plt.imshow(equalized_image)
plt.show()

Output:

Equalized

In this example, the image is first loaded from a file using the
cv2.imread() function. It is then converted to grayscale using the
cv2.cvtColor() function. The cv2.equalizeHist() function is then
called and passed the grayscale image data as an argument. The
equalized image data is stored in the equalized_image variable.
Finally, the modified image is saved to a file using the cv2.imwrite()
function.
Note that the cv2.equalizeHist() function only works on grayscale
images. If you want to equalize the histogram of a color image, you
will need to convert the image to a color space that separates the
intensity values (such as the YCrCb color space) and apply
histogram equalization to the intensity channel. You can then
convert the image back to the original color space if desired.

Other Techniques

Image enhancement is a wide field that involves adjusting images

to improve their visual quality or to make them more suitable for
further analysis. There are many techniques for enhancing images,
such as:
 Morphological transformations: These are operations
based on the image shape. They are typically applied to
binary images, but can also be used with grayscale images.
Examples include dilation, erosion, opening, closing, etc.
Operations can be used to enhance or modify the shape or
 structure of objects in an image. To apply morphological
operations with OpenCV and Python, you can use functions
such as erode, dilate, and morphologyEx.
 Edge detection: OpenCV provides several functions for
performing edge detection, such as Canny(), Sobel(), and
Laplacian(). These functions can be used to identify edges
in an image by looking for sharp changes in pixel intensity.
 Color correction: OpenCV provides several functions for
adjusting the colors in an image, such as cvtColor() and
inRange(). These functions can be used to perform tasks
such as color balance, color grading, and white balancing.
 Image gradients: OpenCV provides several functions for
computing image gradients, such as Scharr(), Sobel(), and
Laplacian(). These functions can be used to highlight
changes in pixel intensity in an image and can be useful for
tasks such as edge detection and image segmentation.
 Image cropping: Cropping techniques can be used to
remove unwanted areas from an image. To crop an image,
you can use the copyMakeBorder function to create a new
image with the desired dimensions, and then copy the
relevant portion of the original image into the new image.
 Image rotation: Rotation techniques can be used to
change the orientation of an image. To rotate an image
with OpenCV, you can use the warpAffine function with a
rotation matrix.
 Image blending: Blending techniques can be used to
combine two or more images together. To blend images
with OpenCV and Python, you can use the addWeighted
function to combine the images using a weighted average.
 Image thresholding: Thresholding techniques can be
used to convert an image to black and white by setting a
threshold value for pixel intensity. To apply thresholding,
you can use the threshold function.
 Image deblurring: Deblurring techniques can be used to
remove blur from an image caused by camera shake, out-
of-focus subjects, or other factors. To deblur an image, you
can use the wiener function, which applies a Wiener filter
to the image.

OpenCV is a powerful library for image processing and computer

vision tasks and it provides many advanced image enhancement
techniques that can be used for a variety of applications. Some of
these techniques are:
 Super-resolution: OpenCV provides the pyrUp() and
pyrDown() functions for upsampling and downsampling
 images, respectively. These functions can be used as part
of a super-resolution algorithm to increase the resolution of
an image.
 Image restoration: OpenCV provides several functions for
image restoration, such as fastNlMeansDenoising() and
fastNlMeansDenoisingColored(). These functions can be
used to remove noise and improve the visual quality of an
image.
 Image fusion: OpenCV provides the addWeighted()
function for combining two images using a weighted sum.
This function can be used to fuse multiple images of the
same scene to create a single image that contains more
information or is of higher quality.
 Image segmentation: OpenCV provides several functions
for image segmentation, including threshold(),
adaptiveThreshold(), and findContours(). These functions
can be used to partition an image into regions or segments
that correspond to different objects or regions of interest.
 Image recognition: OpenCV provides several functions
for image recognition, including HOGDescriptor() and
SIFT(). These functions can be used to extract features
from an image and train a machine-learning model to
recognize objects or scenes.
 Object detection: OpenCV provides several functions for
object detection, including HOGDescriptor() and SIFT().
These functions can be used to detect and locate objects in
an image or video in real time.
 Image registration: OpenCV provides the
registerTranslation() function for aligning or registering two
or more images of the same scene. This function can be
used to align images from different sensors or from
different viewpoints.
 Image stitching: Image stitching techniques can be used
to combine multiple images into a single panoramic or
mosaic image. To apply image stitching with OpenCV and
Python, you can use techniques such as feature matching,
which matches the features in the source images to create
a common reference frame, and image warping, which
warps the images to align them with the reference frame.