25-02-2025

Image Enhancement

What’s an image?

• An image refers to a 2D light intensity function

f(x,y), where (x,y) denote spatial coordinates and
the value of f at any point (x,y) is proportional to
the brightness or gray levels of the image at that
point.

1
 25-02-2025

Image Types
• Monochrome Image (Black and White Image)

• Grey Scale image

• Color Image

Pixel intensity value

Consider the following
image (2724x2336 pixels)
f(1,1) = 103 to be 2D function or a
matrix with rows and
Pixel location columns

In 8-bit representation
Pixel intensity values
rows columns change between 0 (Black)
and 255 (White)
f(645:650,1323:1328) =
83 82 82 82 82 82
82 82 82 81 81 81
82 82 81 81 80 80
82 82 81 80 80 79
80 79 78 77 77 77
80 79 78 78 77 77

f(2724,2336) = 88

2
 25-02-2025

Image Representation

Image Representation

3
 25-02-2025

Image Enhancement
• Goal: process an image so that the result is more
suitable than the original image for a specific
application

Two categories

• Spatial domain
• Direct manipulation of pixels
• Point processing

• Neighborhood processing

• Frequency domain
• Modify the Fourier transform of an image

4
 25-02-2025

Spatial Domain Methods

• In these methods an operation (linear or non-
linear) is performed on the pixels in the
neighborhood of coordinate (x,y) in the input image
F, giving enhanced image F’

g(x,y) = T[f(x,y)]

Point Processing

10

5
 25-02-2025

Point processing is used to transform an image by

operating on individual pixels.
If array A represents an input image then an output
array B is produced by a transformation
B[x, y] = T * A[x, y]

11

1. Digital Negative
• Means inverting the grey levels
• Black in the original image will look white and vice-versa

12

6
 25-02-2025

1. Digital Negative contd…

• For L gray levels the transformation function is
s =T(r) = (L - 1) - r

13

Example: Find the digital negative

of the image given below
4 3 2 1
3 1 2 4
5 1 6 2
2 3 5 6

14

7
 25-02-2025

Digital Negative

15

2. Contrast Stretching

16

8
 25-02-2025

2. Contrast Stretching contd…

• Basic idea is to increase the contrast of an image by
making the dark portions darker and bright
portions brighter
• we stretch the minimum and maximum intensity
values present to the possible minimum and
maximum intensity values.

17

Contrast Stretching
• To increase the dynamic range of the gray levels in
the image being processed.

18

9
 25-02-2025

contd…
• The locations of (r1,s1) and (r2,s2) control the shape of
the transformation function.

• If r1= s1 and r2= s2 the transformation is a linear function and

produces no changes.
• If r1=r2, s1=0 and s2=L-1, the transformation becomes a
thresholding function that creates a binary image.
• Intermediate values of (r1,s1) and (r2,s2) produce various
degrees of spread in the gray levels of the output image, thus
affecting its contrast.
• Generally, r1≤r2 and s1≤s2 is assumed.

19

Example

20

10
 25-02-2025

Example: Apply contrast stretching to the image given below.

Use r1=3, r2=5, s1=2, s2=6

4 3 2 1
3 1 2 4
5 1 6 2
2 3 5 6

21

For a point r,s,

α=

𝑠1 − 0
∝=
𝑟1 − 0 For a point r, s

β=
𝑠2 − 𝑠1
𝛽=
𝑟2 − 𝑟1
For a point r, s
𝑚𝑎𝑥 − 𝑠2 ϒ=
𝛾=
𝑚𝑎𝑥 − 𝑟2

22

11
 25-02-2025

r s
0

23

Input Image Output Image

4 3 2 1
3 1 2 4
5 1 6 2
2 3 5 6

24

12
 25-02-2025

3. Log Transformations
• s = c log(1+r)

◼ Enhances the low intensity pixel

values while compressing the higher
intensity
◼ Compress the dynamic range of
images with large variation in pixel
values
◼ The technique of compressing
dynamic range is known as dynamic
range compression
◼ Log operator is an excellent
compressing function

25

Example: Log Transformations

log

26

13
 25-02-2025

4. Power-law transformations
• s=cr
• >1 darkens the bright regions
• <1 brightens the dark regions
• : gamma
• display, printers, scanners
follow power-law
• Gamma correction
• Non linearities encountered
during image capturing,
printing and displaying can
be corrected using gamma
correction

27

Power-law: <1

• Expand dark gray

levels

=0.6

=0.4 =0.3
28

14
 25-02-2025

Power-law: >1

• Expand light gray

levels

=3

=4 =5
29

5. Thresholding
• It is a way to create a binary image from a
grayscale or full-color image.
• divides the foreground from the background in
an image.

30

15
 25-02-2025

5. Thresholding contd…
• Simple Thresholding/Binary Thresholding
• a standard threshold value is set
• each pixel value is compared with the threshold value.
• If the pixel value is less than the mentioned threshold
value then the value is set to 0 or else it is set to the
maximum value.

31

Example: Apply thresholding to the image given below. Assume

the threshold value = 4

4 3 5 2
3 6 4 6
2 2 6 5
7 6 4 1

32

16
 25-02-2025

Example

33

import cv2
from google.colab.patches import cv2_imshow
import matplotlib.pyplot as plt

image_path = "/content/sample_image.jpg"

def apply_threshold(image_path, threshold_value=127):

# Read the image
original_image = cv2.imread(image_path,
cv2.IMREAD_GRAYSCALE)

# Check if the image is loaded successfully

if original_image is None:
print("Error: Image not found!")
return

34

17
 25-02-2025

# Apply thresholding
_, thresholded_image = cv2.threshold(original_image,
threshold_value, 255, cv2.THRESH_BINARY)

# Display the original and thresholded images

print("Original Image:")
cv2_imshow(original_image) # For Colab

print("Thresholded Image:")
cv2_imshow(thresholded_image) # For Colab

# Save the result (optional)

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

# Example usage
image_path = "/content/sample_image.jpg" # Replace with your
image's path
apply_threshold(image_path, threshold_value=127)

35

36

18
 25-02-2025

6. Grey-Level Slicing
• It manipulates a group of intensity levels in an
image up to a specific range by diminishing the
rest
• Useful for highlighting features in an image
• Used in medical and satellite images such as
X-ray flaws and CT scans.

39

Perform grey level slicing with r1=2 and r2=5

4 3 5 2
3 6 4 6
2 2 6 5
7 6 4 1

40

19
 25-02-2025

Perform grey level slicing with r1=2 and r2=5 (with background)

4 3 5 2
3 6 4 6
2 2 6 5
7 6 4 1

41

42

20
 25-02-2025

1. Original Input Image 2. Digital Negative

3. Thresholding 4. Grey Level Slicing with

Background

43

7. Bit Plane Slicing

• Pixels are digital numbers, each one
composed of bits.

44

21
 25-02-2025

Bit-Plane Slicing
• To highlight the contribution made to the total
image appearance by specific bits.

• i.e. Assuming that each pixel is represented by 8 bits, the

image is composed of 8 1-bit planes.
• Plane 0 contains the least significant bit and plane 7
contains the most significant bit.
• Only the higher order bits (top four) contain visually
significant data. The other bit planes contribute the
more subtle details.

45

Bit-Plane Slicing: example

46

22
 25-02-2025

7 6

5 4 3

2 1 0

47

Example

48

23
 25-02-2025

49

50

24