A NOVEL EVOLUTIONARY FRAMEWORK FOR FEATURE MATCHING

Biao Wang, Chaoying Tang

2008

Abstract

The paper presents a new feature matching scheme based on the Queen-bee Evolution for two uncalibrated images. Matching features needs an exhaustive search in a vast space, for which evolutionary algorithms are recommended recently. This paper propose a simple and effective algorithm. We intuitively encode a string of integer numbers assigned to the features as chromosomes and develop a novel crossover operator respectively which can preserve the position information without any disruption. We also tailor swap mutation operator to prevent from premature convergence and invalid solutions. As a result, the proposed algorithm can quickly achieve the global or near global optimal solution cooperating with the linear ranking selection and the elitist replacement. Meanwhile, it is a more general framework for matching various types of features. The experimental results illustrate the performance of the proposed approach.

References

  1. Beveridge, J. R., Balasubramaniam, K., and Whitley, D. (2000). Matching horizon features using a messy genetic algorithm. Computer Methods in Applied Mechanics and Engineering, 186:499-516.
  2. Bierwirh, C., Mattfeld, D. C., and Kopfer, H. (1996). On permutation representations for scheduling problems. In Lecture Notes on Computer Science, volume 1141, pages 310-318. Springer-Verlag, Berlin Heidelberg, New York.
  3. Brizuela, C. A. and Aceves, R. (2003). Experimental genetic operators analysis for the multi-objective permutation flowshop. In Lecture Notes on Computer Science, volume 2632, pages 578-592. Springer-Verlag.
  4. Chai, J. and Ma, S. (1998). An evolutionary framework for stereo correspondence. In the 14th International Conference on Pattern Recognition, pages 16-20, Brisbane, Australia.
  5. Harris, C. and Stephens, M. (1988). a combined corner and edge detector. In the Fourth Alvey Vision Conference, pages 147-151, Manchester.
  6. Jung, S. H. (2003). Queen-bee evolution for genetic algorithm. Electronics Letters, 39(6):575-576.
  7. Ruichek, Y., Issa, H., , and Postaire, J.-G. (2000). Genetic approach for obstacle detection using linear stereo vision. In the IEEE Intelligent Vehicles Symposium, Dearborn (MI), USA.
  8. Schmid, C., Mohr, R., and Bauckhage, C. (2000). Evaluation of interest point detectors. International Journal of Computer Vision, 37(2):151-172.
  9. Starkweather, T., McDaniel, S., and Mathias, K. (1991). A comparison of genetic sequencing operators. In Belew, R. and Booker, L., editors, the 4th International Conference on Genetic Algorithms, pages 69- 76, Morgan Kaufmann.
  10. Yuan, X., Zhang, J., and Buckles, B. P. (2004). Evolution strategies based image registration via feature matching. Information Fusion, 5:269-282.
  11. Zhang, B.-T. and Kim, J.-J. (2000). Comparison of selection methods for evolutionary optimization. Evolutionary Optimization, An International Journal on the Internet, 2(1):55-70.
  12. Zhang, Z., Deriche, R., Faugeras, O., and Luong, Q.-T. (1994). A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Research report 2273, INRIA, Sophia-Antipolis, France.
Download


Paper Citation


in Harvard Style

Wang B. and Tang C. (2008). A NOVEL EVOLUTIONARY FRAMEWORK FOR FEATURE MATCHING . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 641-644. DOI: 10.5220/0001075606410644


in Bibtex Style

@conference{visapp08,
author={Biao Wang and Chaoying Tang},
title={A NOVEL EVOLUTIONARY FRAMEWORK FOR FEATURE MATCHING},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={641-644},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001075606410644},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - A NOVEL EVOLUTIONARY FRAMEWORK FOR FEATURE MATCHING
SN - 978-989-8111-21-0
AU - Wang B.
AU - Tang C.
PY - 2008
SP - 641
EP - 644
DO - 10.5220/0001075606410644