Abstract

The shape is one of most important feature for characterising an object. However, most shapes that are expressed with primitive uniform features have difficulty reflecting their logical and structural properties. In this paper, we propose a structural analysis scheme for the shape feature structured by logical properties, as well as a similar retrieval method. A shape is represented as a set of curve segments with a specific pattern. As a fundamental unit, a curve segment has adaptive features based on the logical property of its pattern. The relationship information of curve segments is expressed as a structural feature. We also use it as a feature for “coarse-fine” matching because our shape features have global characteristics as a structural feature and local characteristics as an adaptive feature of shape. Our experiments show that structural-adaptive features through logical analysis result in effectively classifying shapes according to their cognitive characteristics. Various experiments show that our approach reduces computational complexity and retrieval cost.

Keywords

Interest Point Logical Property Curve Segment Adaptive Feature Contour Point 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Gudivada, V.N., Raghavan, V.V.: Content-Based Image Retrieval Systems, pp. 18–22. IEEE Computer, Los Alamitos (1995)Google Scholar
  2. 2.
    Leung, C.H.C., Zheng, Z.J.: Image Data Modeling for Efficient Content Indexing. In: Proc. Intl. Workshop on Multi-Media Database Management Systems, August 28-30, pp. 143–150 (1995)Google Scholar
  3. 3.
    Narasimhalu, D.: Special Section on Content-based Retrieval. ACM Multimedia Systems (3), 1–2 (1995)Google Scholar
  4. 4.
    Safar, M., Shahabi, C., Sun, X.: Image Retrieval By Shape: A Comparative Study. IEEE Intl. Conference on Multimedia and Expo. (I), 141–154 (2000)Google Scholar
  5. 5.
    Geiger, D., Liu, T.L., Kohn, R.V.: Representation and Self-similarity of Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(1), 86–99 (2003)CrossRefGoogle Scholar
  6. 6.
    Mokhtarian, F.: Silhouette-based Isolated Object Recognition through Curvature Scale Space. IEEE Transactions on Pattern Analysis and Machine Intelligence 17, 539–544 (1995)CrossRefGoogle Scholar
  7. 7.
    Fudos, I., Palios, L., Pitoura, E.: Geometric-similarity Retrieval in Large Image Bases. In: Proc. of 18th International Conference on Data Engineering, pp. 441–450 (2002)Google Scholar
  8. 8.
    Suganthan, P.N.: Shape Indexing Using Self-organizing Maps. IEEE Transactions on Neural Networks 13(4), 835–840 (2002)CrossRefGoogle Scholar
  9. 9.
    Mignotte, M.: A new and simple shape descriptor based on a non-parametric multi-scale model. In: Proc. of. International Conference on Image Processing, vol. 1, pp. 445–448 (2002)Google Scholar
  10. 10.
    Milios, E., Petrakis, E.G.M.: Shape Retrieval Based on Dynamic Programming. Trans. Image Proc. 9(1), 141–146 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Nanhyo Bang
    • 1
  • Kyhyun Um
    • 1
  1. 1.Department of Computer and Multimedia EngineeringDongguk UniversitySeoulKorea

Personalised recommendations