Synthesising surface matching algorithms using the correspondence framework


Computer vision tasks such as registration, modeling and object recognition, are becoming increasingly useful in industry. Each of these applications employs correspondence algorithms to compute accurate mappings between partially overlapping surfaces. In industry, it is essential to select an appropriate correspondence algorithm for a given surface matching task. A correspondence framework has recently been proposed to assist in the selection and creation of correspondence algorithms for these tasks. This paper demonstrates how to use the correspondence framework to create a new surface matching algorithm, which uses stages of an existing model matching algorithm. The efficiency with which the new algorithm is created using the correspondence frame work is emphasized. In addition, results show that the new algorithm is both robust and efficient.

This is a preview of subscription content, log in to check access.


  1. 1.

    A. Ashbrook, R. Fisher, N. Werghi, and C. Robertson, “Aligning Arbitrary Surfaces Using Pairwise Geometric Histograms,” in Proceedings of Noblesse Workshop on Non-linear Model Based Image Analysis, 1998, pp. 103–108.

  2. 2.

    C. Chen and Y. Huang, “RANSAC-based DARCES: A New Approach to Fast Automatic Registration of Partially Overlapping Range Images,” IEEE Trans. on Pattern Analysis and Machine Intelligence 21(11), 1229–1234 (1999).

    Article  Google Scholar 

  3. 3.

    A. E. Johnson, “Spin-Images: A representation for 3-D Surface Matching,” PhD thesis (Carnegie Mellon University, Pittsburgh, Pennsylvania, August 1997).

    Google Scholar 

  4. 4.

    P. Krsek, T. Pajdla, V. Hlavac, and R. Martin, “Range Image Registration Driven by Hierarchy of Surface Differential Features,” in Proceedings of the 22nd Workshop of the Austrian Assoc. for Pattern Recognition, 1998, pp. 175–183.

  5. 5.

    R. Osada, T. Funkhouser, B. Chazelle, and D. Dobkin, “Matching 3D Models with Shape Distributions,” in Proceedings Int. Conf. on Shape Modeling and Applications, 2001, pp. 154–166.

  6. 6.

    B. M. Planitz, A. J. Maeder, and J. A. Williams, “The Correspondence Framework for Automatic Surface Matching” in Proceedings of Australian and New Zealand Conf. on Intelligent Information Systems, 2003, pp. 319–324.

  7. 7.

    K. Pulli, “Multiview Registration for Large Data Sets,” in Proceedings of the 2nd Int. Conf. on 3-D Digital Imaging and Modeling, 1999, pp. 160–168.

Download references

Author information



Additional information

The text was submitted by the authors in English.

Birgit Maria Planitz, born in 1978, received B. Engineering (Hons) degree at the Queensland University of Technology (QUT) in Brisbane, Australia (2001). Dr. Planitz then continued her studies at QUT, enrolling in a PhD. The PhD was in the field of computer vision, specializing in three-dimensional surface matching. Dr. Planitz graduated from her postraduate degree in 2005, with two major journal publications, six conference papers and a technical report. She is currently working for the e-Health Research Centre/CSIRO ICT Centre. Dr. Planitz is a member of the Australia Pattern Recognition Society.

Anthony John Maeder, born 1958, graduated with B. Science (Hons) from University of Witwatersrand in 1980 and M. Science from the University of Natal in 1982. He was awarded his PhD in 1992 by Monash University. Dr. Maeder is currently the Research Director, E-Health Research Centre/CSIRO ICT Centre and Adjunct Professor, Faculty of Health Sciences, University of Queensland. His research areas include digital image processing, image and video compression, medical imaging, computer graphics and visualization. Dr. Maeder has 200 publications consisting of 10 monographs and proceedings, 20 journal papers and 180 conference papers. He is a fellow of the Institution of Engineers Australia; a member of IEEE, ACM, ACS, HISA; a member of SPIE International Technical Committee for Medical Imaging; and a member of national executive committee of the Australian Pattern Recognition Society.

John Alan Williams, born in 1973, was awarded his PhD from the Queensland University of Technology (QUT), Australia, in 2001. He was previously awarded undergraduate degrees in Electronic Engineering and Information Technology (Hons), also from QUT, in 1995. He is currently employed at the School of ITEE at The University of Queensland, Brisbane, Australia, where he holds the position of Research Fellow. Dr. William’s research interests include reconfigurable computing and realtime embedded systems, as well as 3D computer vision and imaging. He has authored 5 refereed journal publications and more than 20 refereed conference publications, and has recently edited the Proceedings of the 2004 IEEE International Conference on Field Programmable Technology. He has been a member of the IEEE for eight years.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Planitz, B.M., Maeder, A.J. & Williams, J.A. Synthesising surface matching algorithms using the correspondence framework. Pattern Recognit. Image Anal. 17, 199–203 (2007).

Download citation


  • Iterative Close Point
  • Local Match
  • Surface Match
  • Iterative Close Point Algorithm
  • Correspondence Algorithm