Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
4K views

Pruning: Advanced Topic in Image Processing

This is a an easy to understand the topic of pruning. Full animated slides enhance the understanding to build the advance knowledge.

Uploaded by

Qaisar Ayub Sheikh
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
4K views

Pruning: Advanced Topic in Image Processing

This is a an easy to understand the topic of pruning. Full animated slides enhance the understanding to build the advance knowledge.

Uploaded by

Qaisar Ayub Sheikh
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 191

Sheikh Qaisar Ayub , Sulma Rashid

Advanced topic in Image Processing

Pruning
By

Qaisar Ayub

sheikhqaisar@gamil.com
Pruning
What ?
A post processing Operation on images

Thinning and skeltonization algorithms tends to leave the parasitic


components
Parasitic Components
Pruning
Pruning
Problem
Our task is to recognize the hand written characters
Solution
Find the skeleton of each character

During the process of skeleton some of the parasitic


components associated in each character

These parasitic components derived due to the non


uniformalities in the strokes composing the character
Pruning
Parasitic

Observe Parasitic Components

Q
Pruning

Achievements

1. What is pruning
2. Parasitic Components
Pruning
To understand the pruning algorithm we take an example of
recognizing the handwritten character ‘a’

After applying the skeltionization algorithm we get the following


structure
Pruning
This is what we are interested to remove
Pruning
Algorithm
Step-01
Suppress the parasitic components by eliminating the end
points

By applying the thinning algorithm on the image we can get


endpoints

Mathematically the thinning algorithm can be written as

X1 = A {B}
Pruning
Algorithm
Step-01

X1 = A {B}

B := Structuring element
{ } := Represent the iteration
A := Input Image
:= Hit or Miss Translation
Pruning
Algorithm
Step-01
X1 = A {B}

Structuring element {B} = B1 B2 B3 B4 B5 B6 B7 B8


B1

B2

B3
B4
Pruning
Algorithm
Step-01
X1 = A {B}
Structuring element {B} = B5 B6 B7 B8

B5 :=

B6:=

B7:=

B8:=
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
No match found Row 01
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning

X1=

After applying thinning 3 times we get X1


Pruning

Achievements

End Point Removing process has


been completed
Pruning
Algorithm
Step-02
Restore the character to its original Form by removing
parasitic branches

Solution
Form a set X2 by which contains all end point in X1
Following equation is used to achieve this
Pruning
Algorithm
Step-02

X1 B1

X1 B2
Pruning
Algorithm
Step-02

X1 B3

X1 B4
Pruning
Algorithm
Step-02

X1 B5

X1 B6
Pruning
Algorithm
Step-02

X1 B7

X1 B8
Pruning

X2=
Pruning

Achievements

End point have been found from X1


Pruning
Algorithm
Step-03

X2=

H= Structuring Element
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning
Pruning

Achievements

Dilation process at end point have


been completed
Pruning
Algorithm
Step-03 Continue…

∩A

∩
Pruning

∩A

X3 =
Pruning

Achievements
Pruning
Algorithm
Step-04
X4 = X1 U X3
Pruning
Algorithm
Step-04
X4 = X1 U X3
Thanks

You might also like