Abstract
Expert system technology has been successfully applied to many practical problems, but there has been little evidence of transfer to computer vision. In this paper we discuss some of the problems confronting computer vision, and present an approach to the development of general knowledge-based vision systems. Our approach involves the building of an intermediate symbolic representation of the image data using knowledge-free segmentation processes. From the intermediate level data, a partial interpretation is constructed by associating an object label with selected groups of the intermediate primitives.
The primary mechanism for generation of initial object hypotheses is a rule-based approach applied to the attributes of the lines, regious, and surfacces in the intermediate symbolic representation. Simple rules are defined as ranges over a feature value which are converted to a vote for an object label; complex rules are constructed via a functional combination of the output from the simple rules. The rules are constructed interactively with visual feedback as part of the knowledge engineering process.
The object hypotheses are used to activate portions of the knowledge network related to verifying or more completely extracting the hypotesized object. Once activated, the procedural components of the knowlede network direct additional more expensive extraction of object features, as well as further grouping, splitting and labelling processes at the intermediate level to construct intermediate events which are in closer agreement with the sotred symbolic object description. We conclude with some principles which could be used to guide knowledge-based vision research.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
R. Davis, Expert Systems: Where are Vaß And Where Do We Go From Here?, AI Magazine S (Spring 1982 ), 3–22.
R. Bajcsy and M. Tavakoli, Computer Recognition of Roads from Satellite Pictures, IEEE Transactions on Systems, Man, and Cybernetics SMC-6 (September 1976), 623–637.
D. Ballard, C. Brown and J. Feldman, An Approach to Knowledge-Directed Image Analysis, Computer Vision Systems (A. Hanson and E. Riseman, eds. ) (1978), Academic Press.
H. Barrow and J. Tenenbaum, MSYS: A System for Reasoning About Scenes, Technical Note 121 ( April 1976 ), AI Center, Stanford Research Institute.
T. Binford, Survey of Model Based Image Analysis Systems, International Journal of Robotics Research 1 (1982), 18–64.
R. Brooks, Symbolic Reasoning Among S-D Models and S-D Images, STAN-CS- 81-861 and AIM-343 ( June 1981 ), Department of Computer Science, Stanford University.
O. Faugeras and K. Price, Aerial Images Using Stochastic Labeling, IEEEPAMI 3 (November 1981), 638–642.
A. Hanson and E. Riseman, VISIONS: A Computer System for Interpreting Scenes, Computer Vision Systems (A. Hanson and E. Riseman, eds.) (1978), 303–333, Academic Press.
T. Kanade, Model Representation and Control Structures in Image Understanding, Proc. IJCAI-5 (August 1977).
M. Levine and S. Shaheen, A Modular Computer Vision System for Picture Segmentation and Interpretation, IEEE PAMI 3 (September 1981), 540–556.
A. Mackworth, Vision Research Strategy: Black Magic, Metaphors, Mechanisms, Miniworlds, and Maps, Computer Vision Systems (A. Hanson and E. Riseman, eds. ) (1978), Academic Press.
M. Nagao and T. Matsuyama, A Structural Analysis of Complex Aerial Photographs (1980), Plenum Press, New York.
Y. Ohta, A Region-Oriented Image-Analysis System by Computer, Ph.D. Thesis (1980), Information Science Department, Kyoto University, Kyoto, Japan.
K.E. Price and R. Reddy, Matching Segments of Images, IEEE PAMI 1 (June 1979), 110–116.
J.M. Tenenbaum and H. Barrow, Experiments in Interpretation-Guided Segmentation, Technical Note 123 (1976), AI Center, Stanford Research Institute.
J. Tsotsos, Knowledge of the Visual Process: Content, Form and Use, Proceedings of 6th International Conference on Pattern Recognition (October 1982), 654–669, Munich, Germany.
Y. Yakimovsky and J. Feldman, A Semantics-Based Decision Theory Region Analyzer, Proceedings of IJCAI-3 (August 1973), 580–588.
D. Marr, Vision (1982), W.H. Freeman and Company, San Francisco.
M. Brady, Computational Approaches to Image Understanding, Computing Surveys 14 (March 1982), 3–71.
P.A. Nagin, A.R. Hanson and E.M. Riseman, Studies in Global and Local Histogram- Guided Relaxation Algorithms, IEEE PAMI PAMI-4 (May 1982), 263–277.
R. Kohler, Integrating Non-Semantic Knowledge into Image Segmentation Processes, Ph.D. Dissertation and COINS Technical Report 84-04 (1984), University of Massachusetts at Amherst.
J.B. Burns, A.R. Hanson and E.M. Riseman, Extracting Linear Features, Proc. of the Seventh International Conference on Pattern Recognition (July 30 - August 2, 1984), Montreal, Canada.
G. Reynolds, et al., Hierarchical Knowledge-Directed Object Extraction Using a Combined Region and Line Representation, Proc. of the Workshop on Computer Vision: Representation and Control (April 30-May 2, 1984), 238–247, Annapolis, Maryland.
T.E. Weymouth, J.S. Griffith, A.R. Hanson and E.M. Riseman, Rule Based Strategies for Image Interpretation, Proc. of AAAI-83 (August 1983), 429–432, Washington, D.C. A longer version of this paper appears in Proc. of the DARPA Image Understanding Workshop (June 1983), 193–202, Arlington, VA.
C.C. Parma, A.R. Hanson and E.M. Riseman, Experiments in Schema-Driven Interpretation of a Natural Scene, COINS Technical Report 80–10 ( April 1980 ), University of Massachusetts at Amherst.
V.R. Lesser and L.D. Erman, A Retrospective View of the Hearsay-II Architecture, Proc. IJCAI-5 (1977), 790–800, Cambridge, MA.
L. Erman, et al., The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty, Computing Surveys 12 (2) (June 1980), 213–253.
T.E. Weymouth, Using Object Descriptions in a Schema Network for Machine Vision, Ph.D. Dissertation, under development, Computer and Information Science Department, University of Massachusetts at Amherst.
J.D. Lowrance, Dependency-Graph Models of Evidential Support, Ph.D. Dissertation and COINS Technical Report 82–26 ( September 1982 ), University of Massachusetts at Amherst.
L. Wesley and A. Hanson, The Use of an Evidential-Based Model for Representing Knowledge and Reasoning about Images in the VISIONS System, Proc. of the Workshop on Computer Vision (August 1982), 14–25, Rindge, New Hampshire.
A. Hanson and E. Riseman, Computer Vision Systems (1978), Academic Press.
G. Shafer, A Mathematical Theory of Evidence (1976), Princeton University Press.
A. Hanson and E. Riseman, A Summary of Image Understanding Research at the University of Massachusetts, COINS Technical Report 83–35 ( October 1983 ), University of Massachusetts at Amherst.
A. Hanson and E. Riseman, Segmentation of Natural Scenes, Computer Vision Systems (A. Hanson and E. Riseman, Eds. ), Academic Press (1978), 129–163.
E. Riseman and A. Hanson, The Design of a Semantically Directed Vision Processor, COINS Technical Report TR 71C-1, University of Massachusetts (February 1975), Revised version COINS Technical Report 75C-1.
E. Riseman and A. Hanson, A Methodology for the Development of General Knowledge-Based Vision Systems, Proc. of the IEEE Workshop on Principles of Knowledge-Based Systems (December 1984), Denver, Colorado.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1985 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Riseman, E.M., Hanson, A.R. (1985). A Methodology for the Development of General Knowledge-Based Vision Systems. In: Brauer, W., Radig, B. (eds) Wissensbasierte Systeme. Informatik-Fachberichte, vol 112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-70840-4_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-70840-4_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-15999-5
Online ISBN: 978-3-642-70840-4
eBook Packages: Springer Book Archive