IMAGE MATCHING USING RELATIONAL GRAPH REPRESENTATION

Lai Chui Yen, Daut Daman, Mohd Shafry Mohd Rahim

Abstract

A stereo matching strategy that involves the usage of structural description from the image is proposed. This structural matching strategy is to address the problem of image features that undergo occlusion and also the missing feature situation. The description of the image scene is done by the construction of a relational graph that described the relationship among image primitives. Consequently, the matching problem is to match two structural descriptions, which is represented by a relational graph. The matching between these relational graphs is determined by comparing these structures using graph theory. The best available match between these relational graphs can be determined by finding the best maximal clique in an association graph.

References

  1. Horaud, R., Skordas, T., 1989, Stereo correspondence through feature grouping and maximal cliques, IEEE Transactions on Pattern Analysis and Machine Intelligence, 11 (11) p.p. 1168-1180.
  2. Liu,Y., Huang, T. S. ,1992, Three-dimensional motion determination from real scene images using straight line correspondences, Pattern Recognition, 25(6), pp. 617-639.
  3. Ohta,Y, Kanade, T.,1985, Stereo by Inra- and InterScanline Search Using Dynamic Programming, IEEE Transactions on Pattern Analysis and Machine Intelligence, 7(2), pp. 159-174.
  4. Pla, F., Marchant, A., 1997, Matching feature points in image sequences through a region-based method, Computer Vision and Image Understanding, 60(3) p.p. 271-285.
  5. Pollefeys,M., 1999 Self-Calibration and Metric 3D Reconstruction from Uncalibrated Image Sequences, Ph.D. Thesis, Katholieke Universiteit Leuven, Belgium.
  6. Strickland, R. N., Mao, Z., 1992, Computing correspondences in a sequence of non-rigid objects, Pattern Recognition, 25(9) p.p 901-912.
  7. Trapp,R., Drüe, S., Hartmann, G., 1988, Stereo matching with implicit dectection of occlusions, Burkhardt, H. and Neumann, B. (eds.), Proc. of 5th European Conference on Computer Vision (ECCV'98), vol.II, pp.17-33.
  8. Zhang, Z. , Shan, Y. ,2001, A progressive scheme for stereo matching”, Pollefeys, M. et al. (eds.): SMILE 2000, Lecture Notes on Computer Science, SpringerVerlag Berlin Heidelberg, vol.2018, pp. 68-85.
  9. Zhang,Z., Faugeras, O. ,1992 , Estimation of Displacements from Two 3-D Frames Obtained from Stereo, IEEE Transactions on Pattern Analysis and Machine Intelligence, 14 (12) p.p. 1141-1156.
Download


Paper Citation


in Harvard Style

Chui Yen L., Daman D. and Shafry Mohd Rahim M. (2006). IMAGE MATCHING USING RELATIONAL GRAPH REPRESENTATION . In Proceedings of the First International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, ISBN 972-8865-39-2, pages 400-406. DOI: 10.5220/0001351704000406


in Bibtex Style

@conference{grapp06,
author={Lai Chui Yen and Daut Daman and Mohd Shafry Mohd Rahim},
title={IMAGE MATCHING USING RELATIONAL GRAPH REPRESENTATION},
booktitle={Proceedings of the First International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP,},
year={2006},
pages={400-406},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001351704000406},
isbn={972-8865-39-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP,
TI - IMAGE MATCHING USING RELATIONAL GRAPH REPRESENTATION
SN - 972-8865-39-2
AU - Chui Yen L.
AU - Daman D.
AU - Shafry Mohd Rahim M.
PY - 2006
SP - 400
EP - 406
DO - 10.5220/0001351704000406