Image Segmentation

1
Image Segmentation
2
Image Analysis Object Recognition
INPUT IMAGE
OBJECT IMAGE
Image Segmentation each object in the image
is identified and isolated from the rest of the
image
3
Image Analysis Object Recognition
x x x x
OBJECT IMAGE
1 2 3 n
FEATURE VECTORS
Feature Extraction measurements or features
are computed on each object identified during
the segmentation step
4
The feature vector for a given pixel consists of
the corresponding pixels from each feature image
the feature vector for an object would be
computed from pixels comprising the object, from
each feature image.
5
Image Analysis Object Recognition
FEATURE VECTORS
OBJECT TYPE WRENCH
Classification each object is assigned to a
class
6
Image Analysis Object Recognition
INPUT IMAGE
OBJECT IMAGE
FEATURE VECTOR
OBJECT TYPE WRENCH
7
Example an automated fruit sorting system
8
Example an automated fruit sorting
system segmentation identify the fruit
objects the image is partitioned to isolate
individual fruit objects
9
Example an automated fruit sorting
system segmentation identify the fruit
objects feature extraction compute a size and
color feature for each segmented region in the
image size - diameter of each object color -
red-to-green brightness ratio (redness
measure)
10
Example an automated fruit sorting
system segmentation identify the fruit
objects feature extraction compute a size and
color feature for each segmented region in the
image classification partition the fruit
objects in feature space
11
(No Transcript)
12
Automatic (unsupervised) image Segementation
difficult problem 1) attempt to
control imaging conditions (industrial
applications) 2) choose sensor which enhance
objects of interest (infrared imaging)
13

• Two Types of Segmentation Algorithms
• Identify discontinuities between
  
• homogeneous regions
• Identify similarity of pixel values within a
• region

14

• Discontinuity based Segmentation Algorithms
• Identify the boundaries between differing regions
  in the image.
• Two popular techniques use
• Spatial filters, gradients, edge linking
• Identification of zero-crossings,
• thresholding

15
Discontinuity based Segmentation detect points,
lines and edges in an image
16
Discontinuity based Segmentation detect points,
lines and edges in an image
-1 -1 -1 -1 8 -1 -1 -1 -1
17
Discontinuity based Segmentation detect points,
lines and edges in an image
-1 -1 -1 -1 8 -1 -1 -1 -1
-1 -1 -1 2 2 2 -1 -1 -1
-1 2 -1 -1 2 -1 -1 2 -1
-1 -1 2 -1 2 -1 2 -1 -1
2 -1 -1 -1 2 -1 -1 -1 2
18
Discontinuity based Segmentation detect points,
lines and edges in an image
-1 -1 -1 -1 8 -1 -1 -1 -1
-1 -1 -1 2 2 2 -1 -1 -1
-1 2 -1 -1 2 -1 -1 2 -1
-1 0 1 -2 0 2 -1 0 1
-1 -2 -1 0 0 0 1 2 1
-1 -1 2 -1 2 -1 2 -1 -1
2 -1 -1 -1 2 -1 -1 -1 2
19
Discontinuity based Segmentation detect points,
lines and edges in an image
-1 -2 -1 0 0 0 1 2 1
-1 0 1 -2 0 2 -1 0 1
Gx
Gy
20
Discontinuity based Segmentation detect points,
lines and edges in an image
-1 -2 -1 0 0 0 1 2 1
-1 0 1 -2 0 2 -1 0 1
Gx
Gy
21
Discontinuity based Segmentation
Gx
Gradient vector
Gy
Edge Linking - used to create connected boundaries
22
Discontinuity based Segmentation
Gx
Gradient vector
Gy
Edge Linking - used to create connected
boundaries - similar points within a
neighborhood are linked
23
Discontinuity based Segmentation
Gx
Gradient vector
Gy
Edge Linking - used to create connected
boundaries - similar points within a
neighborhood are linked magnitude of gradient
vector Gx Gy
1
2
2
2
24
Discontinuity based Segmentation
Gx
Gradient vector
Gy
Edge Linking - used to create connected
boundaries - similar points within a
neighborhood are linked magnitude of gradient
vector Gx Gy
approximated as Gx Gy
1
2
2
2
25
Discontinuity based Segmentation
Gx
Gradient vector
Gy
Edge Linking - used to create connected
boundaries - similar points within a
neighborhood are linked magnitude of gradient
vector orientation of edges
ang(x,y) tan ( )
-1
Gy
Gx
26
Discontinuity based Segmentation
Gx
Gradient vector
Gy
Edge Linking - used to create connected
boundaries - similar points within a
neighborhood are linked magnitude of gradient
vector orientation of edges
27
Discontinuity based Segmentation Identify zero
crossings
28
Discontinuity based Segmentation Identify zero
crossings
0 -1 0 -1 4 -1 0 -1 0
Laplacian Filter
29
Discontinuity based Segmentation Identify zero
crossings
0 0 -1 0 0 0 -1 -2 -1 0 -1 -2
16 -2 0 0 -1 -2 -1 0 0 0 -1 0
0
Laplacian Of a Gaussian
30
Discontinuity based Segmentation Identify zero
crossings
Original image
LoG
31
Discontinuity based Segmentation Identify zero
crossings
Original image
LoG
Outline of Thresholded LoG
Thresholded LoG
32
Similarity based Segmentation - Simple
thresholding - Split and Merge - Recursive
thresholding
33
Similarity based Segmentation - Simple
thresholding - Split and Merge - Recursive
thresholding
34
Single Level Thresholding
0, g lt TH G - 1, TH lt g
Tg
35
Single Level Thresholding
0, g lt TH G - 1, TH lt g
Tg
36
Single Level Thresholding
37
Single Level Thresholding
0, g lt TH G - 1, TH lt g
Tg
38
Multiple Level Thresholding
0, g lt TH1 G - 1, TH1 lt g lt TH2 0, g gt
TH2
Tg
39
Similarity based Segmentation - Simple
thresholding - Split and Merge - Recursive
thresholding
40
Split and Merge 1) split region into four
disjoint quadrants if P(Rj) FALSE 2)
merge any adjacent regions Rj and Rk if P(Rj
Rk) TRUE 3) stop when no splitting or
merging is possible
41
Split and Merge
42
Split and Merge
43
Split and Merge
44
Split and Merge
45
Split and Merge
46
Split and Merge
47
Split and Merge
1
2
4
3
48
Split and Merge
1
2
4
3