Image Processing and Pattern IPPR_Lecture9.ppt

IOE Image processing unit 9

1. Digital Image Processing
Image Segmentation

2. 2
of
47
The Segmentation Problem

3. 3
of
47
The Segmentation Problem
Segmentation attempts to partition the pixels
of an image into groups that strongly
correlate with the objects in an image
Typically the first step in any automated
computer vision application

4. 4
of
47
Segmentation Examples
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

5. 5
of
47
Image Segmentation
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

6. 6
of
47
Image Segmentation
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

7. 7
of
47
Detection Of Discontinuities
There are three basic types of grey level
discontinuities that we tend to look for in
digital images:
–Points
–Lines
–Edges
We typically find discontinuities using masks
and correlation

8. 8
of
47
Detection Of Discontinuities

9. 9
of
47
Detection Of Discontinuities

10. 10
of
47
Point Detection
Point detection can be achieved simply
using the mask below:
Points are detected at those pixels in the
subsequent filtered image that are above a
set threshold
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

11. 11
of
47
Point Detection (cont…)
Images taken from Gonzalez & Woods, Digital Image Processing (2002)
X-ray image of
a turbine blade
Result of point
detection
Result of
thresholding

12. 12
of
47
Line Detection
The next level of complexity is to try to
detect lines
The masks below will extract lines that are
one pixel thick and running in a particular
direction
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

13. 13
of
47
Line Detection
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

14. 14
of
47
Line Detection (cont…)
Images taken from Gonzalez & Woods, Digital Image Processing (2002)
Binary image of a wire
bond mask
After
processing
with -45°line
detector
Result of
thresholding
filtering result

15. 15
of
47
Edge Detection
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

16. 16
of
47
Edge Detection
An edge is a set of connected pixels that lie
on the boundary between two regions
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

17. 17
of
47
Derivative Operators
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

18. 18
of
47
Edges & Derivatives
We have already spoken
about how derivatives
are used to find
discontinuities
1
st
derivative tells us
where an edge is
2
nd
derivative can
be used to show
edge direction
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

19. 19
of
47
Derivatives & Noise
Derivative based edge detectors are
extremely sensitive to noise
We need to keep this in mind
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

20. 20
of
47
Common Edge Detectors
Given a 3*3 region of an image the following
edge detection filters can be used
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

21. 21
of
47
Edge Detection Example
Images taken from Gonzalez & Woods, Digital Image Processing (2002)
Original Image Horizontal Gradient Component
Vertical Gradient Component Combined Edge Image

22. 22
of
47
Edge Detection Example
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

23. 23
of
47
Edge Detection Example
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

24. 24
of
47
Edge Detection Example
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

25. 25
of
47
Edge Detection Example
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

26. 26
of
47
Laplacian Edge Detection
We encountered the 2
nd
-order derivative
based Laplacian filter already
The Laplacian is typically not used by itself
as it is too sensitive to noise
Usually when used for edge detection the
Laplacian is combined with a smoothing
Gaussian filter
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

27. 27
of
47
Laplacian Edge Detection
Images taken from Gonzalez & Woods, Digital Image Processing (2002)

28. 28
of
47
Edge Linking and boundary
detection

29. 29
of
47
Edge Linking : local processing

30. 30
of
47
Edge Linking : local processing

31. 31
of
47
Edge Linking : local processing

32. 32
of
47
Summary
In this lecture we have begun looking at
segmentation, and in particular edge detection
Edge detection is massively important as it is
in many cases the first step to object
recognition