Advertisement

Chain code-based shape representation and similarity measure

  • Guojun Lu
Content-Based Search and Retrieval
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1306)

Abstract

Object shape is an important feature of images and is used in content-based image retrieval. Two important issues of shape based image retrieval are how to find a shape representation which is invariant to translation, scale and rotation, and a similarity measure which conforms with human perception. The purpose of this paper is to present a shape representation and similarity measure which meet these requirements.

We first describe a normalization process to obtain the unique chain code for each shape which is invariant to translation, scale and rotation. The unique chain code is suitable for shape representation but it is difficult to calculate shape similarity based shape chain codes. We then derive an alternative shape representation based on which shape similarity can be computed easily. Experiments show that the proposed shape representation and similarity measure compare favourable with the Fourier descriptor-based method in both retrieval effectiveness and efficiency.

Keywords

chain code shape representation and similarity measure image retrieval 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Jain, R. (ed.), “NSF Workshop on Visual Information Management Systems: Workshop Report”, Proceedings of the Conference on Storage and Retrieval for image and Video Databases, SPIE Proceedings Series, Vol. 1908, 1993, pp. 198–218.Google Scholar
  2. [2]
    Jain, R., Pentland, A. P. and Petkovic, D., “Workshop report: NSF-ARPA Workshop on Visual Information Management Systems”, June 1995, URL: http:// vision.ucsd.edu/papers/ VimsReport95. html.Google Scholar
  3. [3]
    Lu, G., Communication and Computing for Distributed Multimedia Systems, Artech House, 1996.Google Scholar
  4. [4]
    Chua T S et al, “A concept-based image retrieval system”, Proceedings of 27th Annual Hawaii International Conference on System Sciences, 4–7 January, 1994, pp.590–598.Google Scholar
  5. [5]
    Niblack W et al,'QBIC Project: querying images by content, using colour, texture, and shape', Storage and Retrieval for image and Video Databases, SPIE Proceedings Series, Vol. 1908, 1993, pp. 173–187.Google Scholar
  6. [6]
    Wu, J. K., et al, “STAR — A multimedia database system for trademark registration”. Proceedings of First International Conference, ADB-94, Vadstena, Sweden, June 21–23, 1994, pp. 109–122.Google Scholar
  7. [7]
    Lam, C. P, Wu, J.K., and Mehtre, B., “STAR — a system for trademark archival and retrieval”, Second Asian Conference on Computer Vision, December 5–8, Singapore, pp. III-214–217Google Scholar
  8. [8]
    Jain, A. K and Vailaya, A., “Image retrieval using color and shape”, Second Asian Conference on Computer Vision, December 5–8, Singapore, pp. II-529–II-533.Google Scholar
  9. [9]
    Gonzalez, R.C. and Wintz, P., Digital Image Processing, 2nd edition, Addison-Wesley, 1987.Google Scholar
  10. [10]
    Pitas, I., Digital Image Processing Algorithms, Prentice Hall, 1993.Google Scholar
  11. [11]
    Mohamad, D., Sulong, G. and Ipson, S. S., “Trademark matching using invariant moments”, Second Asian Conference on Computer Vision, December 5–8, Singapore, pp. I-439–I-444.Google Scholar
  12. [12]
    Cortelazzo, G. et al., “Trademark shapes description by string-matching techniques”, Pattern Recognition, Vol.27, No.8, pp. 1005–1018, 1994.Google Scholar
  13. [13]
    Mehrotra, R. and Gary, J. E, “Similar-shape retrieval in shape data management”, Computer, September 1995, pp. 57–62.Google Scholar
  14. [14]
    Jagadish, H. V, “A retrieval technique for similar shapes”, Proceedings of ACM SIGMOD, Colorado, May 1991, pp.208–217.Google Scholar
  15. [15]
    Kauppinen, H., Seppanen, T. and Pietikainen, M., “An experimental comparison of autoregressive and Fourier-based descriptors in 2D shape classification”, IEEE Transactions on PAMI, vol. 17, no. 2, Feb. 1995, pp. 201–207.Google Scholar
  16. [16]
    Sajjanhar, A. et al, “An experimental study of moment invariants and Fourier descriptor for shape based image retrieval”, Technical report, Gippsland School of Computing and Information Technology, Monash University, 1996. (Copies of the report can be obtained from Atul Sajjanhar on atuls@fcit.monash.edu.au)Google Scholar
  17. [17]
    Scassellati, B. et al, “Retrieving images by 2D shape: a comparison of computation methods with human perceptual judgements”, Storage and Retrieval for image and Video Databases II, 7–8 Feb. 1994, San Jose, California, USA, SPIE Proceedings Series, Vol. 2185, pp.2–14.Google Scholar
  18. [18]
    Frakes, W. B. and Baeza-Yates. R. (ed.), Information Retrieval: Data Structures and Algorithms, Prentice Hall, 1992.Google Scholar
  19. [19]
    Salton, G. and McGill, M. J., Introduction to Modern Information Retrieval, McGraw-Hill Book Company, 1983.Google Scholar
  20. [20]
    Lu, G. and Sajjanhar, A., “Region-Based Shape Representation and Similarity Measure Suitable For Content Based Image Retrieval”, Technical report, Gippsland School of Computing and Information Technology, Monash University 1996. (A copy of the report can be obtained from Atul Sajjanhar on atuls@fcit.monash.edu.au)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Guojun Lu
    • 1
  1. 1.Gippsland School of Computing and Information TechnologyMonash UniversityChurchillAustralia

Personalised recommendations