A model-directed image understanding system for computer vision

ABSTRACT

An important research topic in AI is the discovery of constraints. As constraints. In this paper, we present a model-directed image understanding prototype to support computer vision, which can recover constraints of an image by means of the spatial relation and spatial reasoning. according to a model. In the prototype, an object is viewed as an arrangement of two types components, viz., crucial component and ordinary component. Under the direction of models, these components are looked for in a top-down manner so that the image can be recognized. For this purpose, knowledge representation and organization of knowledge base are also presented. Some problems on this research are discussed and some reasons of this research as conclusions are also given to serve the future research.

REFERENCES

• 1: Roland T. Chin , Charles R. Dyer, Model-based recognition in robot vision, ACM Computing Surveys (CSUR), v.18 n.1, p.67-108, March 1986 [doi>10.1145/6462.6464]
• 2: Azriel Rosenfeld," Image Analysis: Problems, Progress and Prospects," Pattern Recognition, Vol. 17, No.l, 1984, pp.3-12.
• 3: Ke Chen and Zhongrong Li," Image Understanding Based on RBC Theory," Proceedings of The 3rd Pan Pacific Computer Conference, Beijing, China, International Academic Publishers, August 1989, pp.906-911.
• 4: K. Chen , Z. Li, An object models development tool to support image understanding system, Proceedings on Graphics interface '90, p.239-243, June 1990, Halifax, Nova Scotia
• 5: C. R. Dyer, Multiscale image understanding, Parallel computer vision, Academic Press Professional, Inc., San Diego, CA, 1987
• 6: Ke Chen, Perceptual Organization, Image Understanding and Fuzzy Techniques in Image Processing, Ph.D. Dissertation, Dept. of Computer Science and Engineering, Harbin Institute of Technology, China, May 1990.
• 7: S. K. Chang , Q. Y. Shi , C. W. Yan, Iconic indexing by 2-D strings, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.9 n.3, p.413-428, May 1987 [doi>10.1109/TPAMI.1987.4767923]
• 8: N. J. Nilsson, Principles of artificial intelligence, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1980
• 9: Irving Biederman," Rcognition-By-Component: A Theory of Human Image Understanding," Psychological Review, Vol. 94, No.2, 1987, pp. 115-147.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Computer vision

Additional Classification:
  G. Mathematics of Computing
  G.2 DISCRETE MATHEMATICS
      G.2.2 Graph Theory
          Subjects: Trees

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Modeling and recovery of physical attributes
      I.2.4 Knowledge Representation Formalisms and Methods
          Subjects: Representations (procedural and rule-based)

General Terms:
Design, Theory