ntation 
Image 
n and 
lee and 
mputer 
Pattern 
mputer 
C IEEE 
)3-215, 
| prioris 
Vision 
ld, A., 
Squares 
fachine 
on via 
achine, 
o Alto, 
Mateo, 
limum- 
tanding 
ntation 
lage in 
nce on 
1990), 
hnique 
IEEE 
dian of 
Icture", 
Istering 
iational 
cember 
n, DC, 
hrough 
Vol.1, 
iption", 
rs and 
estimation by minimum descriprion length", The annals of 
statistics, 1983, Vol.11, no.2, 416-431. 
Rissanen, J., "Universal coding, infromation, prediction, 
and estimation", IEEE Transactions on Information 
Theory, Vol.IT-30, No.4, July, 1984. 
Rodriquez, A.A. and Mitchell, O.R., "Image segmentation 
by background extraction refinements", SPIE Vol.1192 
intelligent Robots and Computer Vision VIII: algorithms 
and techniques (1989). 
Snyder, W., Bilbro, G., Logenthiran, A. and Rajala, S., 
"Optimal thresholding - a new approach", Pattern 
Recognition Letters 11 (1990) 803-810. 
Sumanaweera, T.S., Healey, G., Lee, B.U., Binford, T.O., 
and Ponce, J., "Image segmentation using geometric and 
physical constraints, Proceedings, Image Understanding 
Workshop (Cambridge, MA, April 6-8, 1988), Morgan 
Kaufmann, San Mateo, CA, 1988, 1091-1099. 
Tsikos, CJ. and Bajcsy, RK., "Segmentation via 
manipulation”, IEEE Transactions on Robotics and 
Automation, Vol.7., No.3, June 1991. 
Zhang, Y., "Utilizing high level knowledge in middle 
level image analysis", ISPRS congress, Commission III, 
Washington, D.C., U.S.A., 1992. 
original image segmented image vecotor data 
     
  
     
  
(A 
dA 2 intensity information 
64% d ly 
dau 
0000 
A 
Wd 
DA 
522582557 
4 
225% 
Ha 
p 
  
shape-based measurement 
€ 
  
vectorization ) 
plit-and-merge (xm 
Fig.1 
original chain code 
  
  
| calculating curvature value | 
  
  
| gaussian laplacian filering | 
  
  
| detecting high curvature points | 
  
  
  
  
  
  
| determining position of first node | 
  
  
| initial partition of boundary | 
  
  
A, 
| optimization of position of one node | 
  
  
  
  
  
  
  
  
(final optimal positions >) 
  
Fig.4 
727