Image Processing Reference
In-Depth Information
Define snake points and
parameters
,
and
Start with first snake point
Initialise minimum energy and
co-ordinates
Determine co-ordinates of
neighbourhood point with
lowest energy
Set new snake point co-
ordinates to new minimum
More
snake
points?
Ye s
No
Finish iteration
Figure 6.4
Operation of the Greedy algorithm
matrix of vectors. Each vector has five elements: two are the
x
and
y
co-ordinates of the
contour point, the remaining three parameters are the values of α , β and γ for that contour
point, set here to be 0.5, 0.5 and 1.0, respectively. The
no
contour points are arranged to
be in a circle, radius
rad
and centre (
xc,yc
). As such, a vector is returned for each snake
point,
point
s
, where (
point
s
)
0
, (
point
s
)
1
, (
point
s
)
2
, (
point
s
)
3
, (
point
s
)
4
are the
x
co-ordinate, the
y
co-ordinate and α
, β and γ
for the particular snake point
s
:
x
s
,
y
s
, α
s
,
β
s
, and γ
s
, respectively.
The first-order differential is approximated as the modulus of the difference between the
average spacing of contour points (evaluated as the Euclidean distance between them), and
the Euclidean distance between the currently selected image point
v
s
and the next contour
point. By selection of an appropriate value of α
(
s
) for each contour point
v
s
, this can
control the spacing between the contour points.
d
ds
2
S
-1
v
||
vv
-
||
- ||
s
i
i
+1
=
vv
-
||
s
s
+1
S
i
=0
2
2
S
-1
(
xx
-
) + (
yy
-
)
i
i
+1
i
i
+1
Σ
i
=
-
(
xx
-
) + (
2
yy
-
)
2
(6.13)
S
s
s
+1
s
s
+1
=0
