Professional Documents
Culture Documents
Segmentation
Statistical methods
Edge-based methods
Region based methods
Tresholding
Growing regions
Clustering
Split/Merge
Morphological methods watershed
Knowledge-based
Template matching....
Digital Image Processing
Segmentation is a complex
task...
Thresholding
? Threshold value?
Bimodal histogram
Thresholding
Multimodal Histogram
Digital Image Processing
Otsu's method
f(x,y) <
Threshold
Edge detection
Edge
Intensity
1.2
1
0.8
0.6
0.4
0.2
0
-0.2
-1.5
0.06
0.04
0.02
0
-0.02
-0.04
-0.06
-1.5
-1
-0.5
Edge
0
0.5
1.5
2.5
3.5
2.5
3.5
2.5
3.5
Minimum
point
-1
x 10-3
5
4
3
2
1
0
-1
-2
-3
-4
-5
-1.5
-1
Maximum
-0.5point
0
0.5
+
-0.5
1.5
Zero
crossing
0.5
1.5
+
2
10
11
12
Growing regions
Select a start (seed) point
Grow the point based on a certain property of
homogeneity (Connectivity should be considered)
Seed point selection:
..for example - highlighted point (Due to specific
property) ...
. (cvFloodFill)
13
An example of growing
regions
14
Clustering
15
K-Means Algorithm
2D
1D
Digital Image Processing
16
K-Means Algorithm
17
2 regions
3 regions
Digital Image Processing
18
K-Means Algorithm
19
20
21
22
23
24
25
26
27
Watershed Segmentation
29
Watershed Segmentation
B Distance
transform
C Image's
complement
D Watershed
://httpwww.mathworks.de/company/newsletters/news_notes/win02/watershed.html
Digital Image Processing
30
Watershed Segmentation on
image gradient
31
Watershed Segmentation
Over-segmentation may occur, especially in noisy images
(gradient enhances the high frequencies!)
Match-based segmentation
Template segmentation
Template matching
Correlation
The operation called correlation
is closely related to convolution.
34
Template matching by
correlation
35
36
http://bigwww.epfl.ch/demo/templatematching/tm_correlation/demo.html
Other Features-based
Segmentation
Segmentation in Videosequences
Background Subtraction
first must be learned a model of the
background
this background model is compared against
the current image and then the known
background parts are subtracted away.
The objects left after subtraction are
presumably new foreground objects.
Establishing a Reference
Images
Establishing a Reference Images:
Difference will erase static object:
When a dynamic object move out completely from its
position, the back ground in replaced.
40