image. However, each method may provide a subset 
of the information necessary to produce a more 
meaningful interpretation of the scene [Chu,90,91] 
[Hsieh] [Shufelt]. It is reasonable to expect that there 
will be complication in fusing the result from edge 
detection and region-based segmentation. Most 
research on this subject falls into four categories: (1) 
pixel-wise logical operations; (2) algorithm for 
specific imaging modalities or processing techniques; 
(3) theoretical approaches using a priori information 
and probabilistic models; and (4) techniques using 
high-level knowledge. Our future scheme will be 
oriented on using high-level constraints to enhance 
the quality of segmentation. 
5. CONCLUSIONS 
In this article, we have proposed an architecture for 
integrated image analysis which enable us to carry 
out image analysis from low-level to high-level and 
from high-level to low-level interactively. We are 
especially interested in the problems of: 1) integrate 
high-level knowledge into image segmentation; 2) 
use structural information for stereo matching; 3) 
integrate image segmentation and stereo matching; 
4) combine the edge-based and region-based 
segmentation. One of major theoretic obstacles is on 
how to combine the knowledge from different 
sources, which has partially answered in this paper. 
ACKNOWLEDGEMENT 
Without the consistent support from Prof.dr.ir. 
M.J.M. Bogaerts, the work presented here would be 
not possible. This research is jointly supported by 
CCGM (Centre for Computer Graphics and 
Mapping), FRANK project and Photogrammetry 
Laboratory, Faculty of Geodesy, TU Delft. FRANK 
is a registered trademark of FRANK system 
supported by Geeris Holding Netherlands BV. 
REFERENCES 
Aloimonos, J.Y., Davis, L.S., and Rosenfeld, A., 
"Maryland progress in image understanding", Image 
Understanding workshop 1990. 
Boyer, K.L, and Kak, A.C., "Structural stereopsis for 
3-D vision", IEEE Transactions on PAMI, Vol.10, 
no.2, March 1988. 
Chu, C.-C. and Aggarwal, J.K., "The integration of 
region and edge-based segmentation", International 
Conference on Computer Vision 1990. 
Chu, C.-C. and Aggarwal, J.K., "The interpretation of 
laser radar images by a knowledge-based system”, 
Machine Vision and Applications (1991) 4:145-163. 
Forsyth, D., Mundy, J.L., Zisserman, A., Coelho, C., 
Heller, A. and Rothwell, C., "Invariant descriptions 
for 3-D object recognition and pose", IEEE 
Transactions on PAMI, Vol.13, No.10, Oct. 1991. 
Fua, P., and Hanson, A.]., "Objective Functions for 
Feature Discrimination: Theory", Image 
Understanding Workshop 1989a. 
Fua, P., and Hanson, A .J., "Objective Functions for 
Feature Discrimination: Applications to 
semiautomated and Automated Feature Extraction", 
Image Understanding Workshop 1989b. 
Fua, P. and Hanson, AJ, "An Optimization 
Framework for Feature Extraction", Machine Vision 
and Applications (1991) 4:59-87. 
Gigus, Z., and Malik, J., "Computing the aspect 
graph for line drawings of polyhedral objects", IEEE 
Transactions on PAMI, Vol.12, no.2, Feb. 1990. 
Helava, U.V., "Object-space least-square correlation", 
Photogrammetric Engineering and Remote Sensing, 
Vol.54, No.6, Part1, June 1988, pp.711-714. 
Haralick RM. and Shapiro, LG, "Image 
segmentation techniques”, Computer Vision, 
Graphics, and Image Processing, vol. 29, 1985, 
100-132. 
Hsieh, Y.C., Perlant, F., and McKeown, D.M,, 
"Recovering 3D information from complex aerial 
imagery", Image Understanding Workshop 1990. 
Hung, S.H.Y., "On the straightness of digital arcs", 
IEEE Transactions on PAMI, Vol. PAMI-7, no.2, 
pp-203-215, 1985. 
Keeler, K., "Map representations and coding-based 
prioris for segmentation”, Inter. Conference on 
Computer Vision and Pattern Recognition, Hawaii, 
1991. 
Koenderink, J.J., and Doorn, A.J. van, "The internal 
representation of solid shape with respect to vision", 
Biol. Cybern., vol.32, pp.211-216, 1979. 
Leclerc, Y.G., Image and boundary segmentation via 
minimal-length encoding on the Connection 
Machine, Proceedings, Image Understanding 
Workshop (Palo Alto, CA, May 23-26, 1989), Morgan 
Kaufmann, San Mateo, CA, 1056-1069. 
Leclerc, Y.G., "Region grouping using the minimum- 
description-length principle", Image Understanding 
Workshop 1990. 
Matsuyama, T., "Knowledge-based aerial image 
understanding systems and expert system for image 
processing”, IEEE Transactions on Geoscience and 
remote sensing, Vol.GE-25, No.3, may 1987 
Matsuyama, T., "Expert systems for image 
processing: knowledge-based composition of image 
analysis processes", Computer Vision, Graphics and 
606