Scribd
Upload
21 views41 pages

Unit-8 Morphologica Image Processing

Uploaded by

jainishramanuj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPSX, PDF, TXT or read online on Scribd
21 views41 pages

Unit-8 Morphologica Image Processing

Uploaded by

jainishramanuj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPSX, PDF, TXT or read online on Scribd
You are on page 1/ 41

Morphological

Image Processing
Unit-8
1
Mathematical morphology
• It is a tool for extracting image component
like boundary , convex hull , skeleton

• These components are useful in the representation and


description of region shape

• Language for mathematical morphology : Set theory

2
Preliminaries
• A be a set in Z2 (Cartesian product of set of real integer)
• If is an element of A then

• If is not an element of A the

• Denoted by ∅
• Set with no element is called or set

3
Preliminaries
• A is subset of B

• Union of A and B

• Intersection of A and B

4
• Disjoint / mutually exclusive sets
Preliminaries
• Complement of A

• Difference of A and B

• Reflection of A

5
• Translation of A by point z = ( z1 , z2 )
Preliminaries

6
Structuring element
• Subimage
• Small in size with respect to original image
• Used to probe an image
• Under study for properties of interest

7
Dilation
• A and B are set of Z2
• Dilation of A by B is denoted by A⊕B

• Also called Growing / Thickening function


• Application : bridging gaps

8
Dilation

9
Dilation example

10
Erosion
• A and B are set of Z2
• Erosion of A by B is denoted by A⊖B

• Also called Shrinking / Thinning function


• Application : eliminating irrelevant details

11
Erosion

12
Erosion & Dilation Example

13
Opening
• Erosion followed by Dilation
• A and B are set of Z2
• Opening of A by B denoted by A∘B

• Application : rounding outward points corners

14
Opening

15
Closing
• Dilation followed by Erosion
• A and B are set of Z2
• Opening of A by B denoted by A•B

• Application : rounding inward corners

16
Closing

17
Closing & Opening example

18
Hit-or-Miss Transformation
• A and B are set of Z2
• Finding match of A and B denoted as A⊛B

19
Hit-or-Miss Example

20
Boundary extraction
• Boundary of A is β(A)
• Extract boundary by subtracting erosion from original image

21
Boundary extraction

22
Region Filling
• Objective is to fill entire region with 1’s
• Beginning with a point P inside the boundary
• All nonboundary (background) points are labeled with 0 and
assign value 1 to point P
• Follow procedure to fill the region with 1’s

where X0 = P
B : symmetric structuring element
23
• Algorithm terminates if Xk=Xk-1
• Result of Xk and A contains the filled set and its boundary
Region Filling

24
Region Filling

25
Extraction of Connected
Components
• A is set of one or more connected components

where X0 = P
B : suitable structuring element

• Algorithm terminates when Xk=Xk-1


• Xk contain connected components
26
Extraction of Connected
Components

27
Extraction of Connected
Components

28
Convex Hull
• Set A is called convex if straight line connecting any 2 points
in A lines entirely inside A
• Convex hull H of set S is smallest convex containing S
• H – S is called convex deficiency

where Bi (i=1,2,3,4) represents 4 structuring elements


X0 i = A
29
Convex Hull

where “conv” indicates convergence in the sense Xki = Xk-1i

• Convex hull of A is

30
Convex Hull

31
Thinning
• Thinning of A using structure element B

• If B is sequence of structuring elements

then 32
Thinning

33
Thickening
• Thickening of A using structure element B

• If B is sequence of structuring elements

then

34
Thickening

35
Skeletons
• If Z is the point of S(A) and (D)z is largest disk centered at Z
contained in A
i.e. one cannot find larger disk than (D)z included in A
then (D)z is the maximum disk
• It touches the boundary of A at 2 or more pints
• Skeleton is terms of erosion and opening

where means erosion of A by B k times 36


Skeletons

37
Pruning
• Apply thinning operation

• Restore the character in original form

38
Pruning
• Perform dilation of end points

• Union of X3 and original image

39
Pruning

40
END
OF
UNIT - 8 41

You might also like