You are on page 1of 40

# 主講人:張緯德

1
 Image segmentation
◦ ex: edge-based, region-based
 Image representation
◦ ex: Chain code , polygonal approximation
signatures, skeletons
 Image description
◦ ex: boundary-based, regional-based
 Conclusion

2
edge-based: point, line, edge detection

3
 There are three basic types of gray-level
discontinuities in a digital image: points, lines, and
edges
 The most common way to look for discontinuities
is to run a mask through the image.
 We say that a point, line, and edge has been
detected at the location on which the mask is
centered if R  T ,where R  w1 z1  w2 z2  ......  w9 z9

4
 Point detection

 Line detection

5
 Edge detection:
 f 
f      fx 
Gx
 
Gy
 y 
1
f  mag (f )  Gx  Gy  2 2 2

Gy
 ( x, y)  tan (
1
)
Gx

6
 Edge detection:
Laplacian operation

2 f 2 f
 f  2  2
2

x y

r2
 r 2   2   2 2
 h( r )   
2
e
  4

7
Region-base: SRG, USRG, Fast scanning

8
 Region growing: Groups pixels or sub-region
into larger regions.
◦ step1:
these grow regions by appending to each
seed those neighboring pixels that have
properties similar to the seed.
◦ step2:
 Region splitting and merging

9
◦ With good connectivity

◦ Initial seed-points:
 different sets of initial seed-point cause different
segmented result
◦ Time-consuming problem

10
 Unseeded region growing:
◦ no explicit seed selection is necessary, the
seeds can be generated by the
segmentation procedure automatically.
◦ It is similar to SRG except the choice of seed
point

11
◦ easy to use
◦ can readily incorporate high level knowledge of the
image composition through region threshold

◦ slow speed

12
 Fast scanning
Algorithm:
◦ The fast scanning
algorithm somewhat
resembles unseeded
region growing
◦ the number of clusters of
both two algorithm would
not be decided before
image passing through
them.

13
14
 Last step:

## ◦ merge small region to big

region

15
◦ The speed is very fast
◦ The result of segmentation will be intact with good
connectivity

◦ The matching of physical object is not good
 It can be improved by morphology and geometric
mathematic

16
 dilation  erosion

## A  B  {c  E N | c  a  b for some a  A and b  B} A ! B  {x  E N x  b  A for every b  B}

17
 dilation  erosion

18
 opening  closing

Erosion=>Dilation Dilation=>Erosion
19
20
21
 Muscle Injury Determination  How to judge for using
image segmentation?

##  Use fast scanning algorithm

to segment it.

0.6
Image of the unhealthy muscle fiber
0.5
Image of the healthy muscle fiber

0.4

0.3
Y

0.2

0.1

-0.1
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
X
22
chain code, polynomial approximation,
signature, skeletons

23
4-direction

8-direction
24
 Merging Techniques  Splitting Techniques

S1
S2

25
r
θ

A
A
r(θ ) r(θ )

2A
A

θ θ
  3 5 3 7   3 5 3 7
 2  2
4 2 4 4 2 4 4 2 4 4 2 4

## Distance signature of Distance signature of

circle shapes rectangular shapes

26
 Step1:
◦ (a) 2  N ( p1 )  6
◦ (b) T ( p1 )  1
◦ (c) p2 p4 p6  0
◦ (d) p4 p6 p8  0
 Step2:
◦ (c’) p2 p4 p8  0

◦ (d’) p2 p6 p8  0

27
boundary descriptor: Fourier descriptor,
polynomial approximation

28
 Step1: s (k )  x(k )  jy (k )

 Step2: (DFT)
1

K 1  j 2 uk / K
a(u )  k 0
s ( k ) e
K
 Step3: (reconstruction)

## if a(u)=0 for u>P-1

s(k )  u 0 a(u)e j 2 uk / K
P 1

◦ Just for closed boundaries

29
 What’s the reason that
previous Fourier
descriptors can’t be s1(k)
used for non-closed (xK1, yK1) s2(k)

Step 2

## method to descript s3(k)

non-closed boundaries?
(a)linear offset
Step 3

(b)odd-symmetric
(c) Odd symmetric extension

extension

30
 The proposed method
is used not only for
non-closed boundaries
but also for closed
boundaries.

##  Why we used proposed

method to descript
closed boundaries
rather than previous
method?

31
 Lagrange Polynomial  Cubic Spline Interpolation
n
P( x)  f ( x0 ) Ln ,0 ( x)   f ( xn ) Ln ,n ( x)   f ( xk ) Ln ,k ( x)
k 0

S(x)

( x  x0 ) ( x  xk 1 )( x  xk 1 ) ( x  xn ) S4
Ln ,k ( x)  S6
( xk  x0 ) ( xk  xk 1 )( xk  xk 1 ) ( xk  xn ) S1 S5
S0
S j ( x j 1 )  f ( x j 1 )  S j 1 ( x j 1 )
S 'j ( x j 1 )  S 'j 1 ( x j 1 )
f ( n1) ( ( x)) S "j ( x j 1 )  S "j 1 ( x j 1 )
f ( x)  P( x)  ( x  x0 )( x  x1 ) ( x  xn )
(n  1)!
x0 x1 x2 x3 x4 x5 x6 xn 7 x

e  f ( x)  P( x)

32
 Proposed method(1) f ( x) f ( x ')

## ◦ Step1: rotate the boundary

and let two end point locate
at x-axis
x x'

## ◦ Step2: use second order

polynomial to approximate
the boundary
f ( x ')
4b a 2
yˆ  2 ( x ' )  b
a
( , b)
2
a 2

b
n 1 2
4b a
e  y ' yˆ  
(a, 0)
y j ' 2 ( x j ' )2  b
2
(0, 0) a
j 0 a 2 x0 ' xn 1 ' x '

33
 Proposed method(2)

how can we do?

## ◦ Step1: use split approach

divide the boundary to
two parts.
ŷ1 ŷ1

y1 '

ŷ2
y2 '
ŷ2

## function to fit the

boundary.

34
Regional descriptors: Topological, Texture

35
 E=V-Q+F=C–H

◦ E: Euler number

## ◦ V: the number of vertices

◦ Q: the number of edges
◦ F: the number of faces
◦ C: the number of
connected component
◦ H: the number of holes

36
 Statistical approaches  nth moment:
un ( z)  i 0 ( zi  m)n p( zi )
L 1
◦ smooth, coarse, regular

L 1
m i 0
zi p( zi )
◦ 2th moment:
 is a measure of gray level
contrast(relative smoothness)
◦ 3th moment:
 is a measure of the skewness
of the histogram
◦ 4th moment:
 is a measure of its relative
flatness
◦ 5th and higher moments:
 are not so easily related to
histogram shape

37
 Image segmentation
◦ speed, connectivity, match physical objects or not…
 match physical objects:
 morphological: how to choose foreground or background?
 geometric mathematic: wrong connection

##  Representation & Description

◦ Boundary descriptor:
 rotation, translation, degree of match boundary,
closed or non-closed boundary

38
 [1] R.C. Gonzalez, R.E. Woods, Digital Image
Processing second edition, Prentice Hall, 2002
 [2] J.J. Ding, W.W. Hong, Improvement Techniques
for Fast Segmentation and Compression
 [3] J.J. Ding, Y.H. Wang, L.L. Hu, W.L. Chao, Y.W.
Shau, Muscle Injury Determination By Image
Segmentation
 [4] J.J. Ding, W.L. Chao, J.D. Huang, C.J. Kuo,
Asymmetric Fourier Descriptor Of Non-Closed
segments

39
Thank you for listening

40