This document discusses image enhancement techniques. It begins by explaining that image enhancement aims to process an image to make it more suitable for a specific application than the original. Techniques can operate in the spatial domain on pixels, the frequency domain on Fourier transforms, or use combinations. Point and local operations modify pixel brightness values. Enhancement factors include dynamic range, bit-planes, and illumination. Morphological operators create structuring elements to perform operations like opening that can remove objects based on size.

2. Image Enhancement
• Principle objective of Image enhancement is to
process an image so that result is more suitable
than original image for specific application.
 Very first step in Digital Image Processing.
 It is purely subjective.
 It is a cosmetic procedure.
 It improves subjective qualities of images.

4. Image enhancement techniques can be divided into
different categories:
Spatial domain : - operate directly on pixels
Frequency domain : - operate on the Fourier transform of an image
Combination Methods:- There are some enhancement techniques
based on various combinations of methods from the first two
categories
Point operations: - modify the brightness value of each pixel
independently
Local operations: - modify the value of each pixel based on
neighboring brightness values

5. Enhancement Factors
• Dynamic Range of Intensity Values.
• Limited number of bit-planes.
• Varying illumination over the image space.
 Brightness
 Contrast
 Color

6. Morphological operators
• Create morphological structuring element (STREL)
• NHOOD is a matrix containing 1's and 0's; the location of the 1's defines the
neighborhood for the morphological operation.
• SE = strel('arbitrary', NHOOD) creates a flat structuring element
where NHOOD specifies the neighborhood.
NHOOD1 =[ 1 1 1;1 1 1];
NHOOD2 =[ 1 1 1;1 0 1; 0 0 0];
SE1 = strel('arbitrary', NHOOD1);
SE2 = strel('arbitrary', NHOOD2);
SE1 = Flat STREL object containing 6
neighbors.
Neighborhood:
1 1 1
1 1 1
SE2 = Flat STREL object containing 5
neighbors.
Neighborhood:
1 1 1
1 0 1
0 0 0

7. • SE = strel('arbitrary', NHOOD, HEIGHT) creates a non flat structuring
element, where NHOOD specifies the neighborhood.
• HEIGHT is a matrix the same size as NHOOD containing the height values
associated with each nonzero element of NHOOD.
• The HEIGHT matrix must be real and finite valued.
NHOOD3 =[ 1 0 0;0 0 1];
HEIGHT = [23 0 0; 0 0 5];
SE3 = strel('arbitrary', NHOOD3, HEIGHT);
SE3 = Nonflat STREL object containing 2 neighbors.
Neighborhood:
1 0 0
0 0 1
Height:
23 0 0
0 0 5

8. Morphologically open image [imopen]
SE = strel(shape, parameters)
• SE = strel('disk', R, N)
• SE = strel('rectangle', MN)
arbitrary, ball, diamond, line, octagon, pair, periodicline, square
Create morphological structuring element [strel]
• IM2 = imopen(IM,SE)
• IM2 = imopen(IM,NHOOD)

9. Morphologically open image with structuring
element disk
original = imread('snowflakes.png')
figure, imshow(original);
Create a disk-shaped structuring element with a radius of 5 pixels.
se = strel('disk',5);
Remove snowflakes having a radius less than 5 pixels by opening it
with the disk-shaped structuring element.
y = imopen(original,se);
figure, imshow(y,[]);

10. Disk Structuring Element R=3

11. original = imread('snowflakes.png')
figure, imshow(original);
Create a rectangle-shaped structuring element with 3 rows and
5 columns.
MN = [3,2];
se = strel(‘rectangle‘, MN);
Remove snowflakes having a radius less than 5 pixels by opening
It with the disk-shaped structuring element.
Opening = imopen(original,se);
figure, imshow(Opening,[]);

12. Rectangle Structuring Element N rows
and M columns

13. Thank You
Manish T I
Email: manishti2004@gmail.com
Website: www.iprg.co.in
FB: ImageProcessingResearchGroup