COMPARISON OF MATCHING STRATEGIES FOR COLOUR IMAGES

Bogusław Cyganek, Łukasz Socha

Abstract

The paper addresses the ubiquitous problem of matching of colour images. Colour plays very important role in human visual system and the question arises how it can influence image matching in case of a computer based vision systems. In this paper the area based matching methods are investigated. Several matching cost functions and different colour spaces (RGB, HSI, YCrCb) are examined. Obtained results for colour are compared with monochromatic methods. Quality of dense disparity maps was verified in two ways: by number of points rejected after cross-checking and by PSNR value between original reference image and its reconstruction from the second reference and disparity map. The main objective of this research is to verify benefits and drawbacks of using colour information for matching versus inevitable costs associated with processing of greater amounts of data.

References

  1. Cyganek, B., 2002. Three Dimensional Image Processing, (in Polish) EXIT Warsaw, Poland.
  2. Koshan, A., 1997. Improving Robot Vision by Colour Information, Proc. 7th Int. Conf. on Artificial Intelligence, Slovakia.
  3. Koshan, A., 1996. Using perceptual attributes to obtain dense depth maps, Proc. of the IEEE Southwest Symposium on Image Analysis and Interpretation, USA, pp. 155-159.
  4. Koshan A., Rodehorst V., Spiller K., 1996. Colour Stereo Vision Using Hierarchical Block Matching and Active Colour Illumination, ICPR 96, Austria, Vol. I, pp. 835-839.
  5. Scharstein, D., 1998. View Synthesis Using Stereo Vision, Lecture Notes on Computer Science No. 1583, Springer, Berlin.
  6. Scharstein, D., Szeliski, R., 2002. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision, Vol. 47, No. 1-3, pp. 7-42.
  7. Tseng, D., Chang, C., 1992. Colour segmentation using perceptual attributes, Proc. 11th Int. Conference on Pattern Recognition, the Netherlands, pp. 228-231.
  8. Wei, B., Liu, Y., Pan, Y., 2003. Using Hybrid Knowledge Engineering and Image Processing in Colour Virtual Restoration of Ancient Murals, IEEE Trans. on Knowledge and Data Eng., Vol. 15, No. 5, pp. 1338- 1343.
  9. Loo P.K., Tan C.L., 2002. Adaptive Region Growing Colour Segmentation for Text using Irregular Pyramid, Technical Report.
Download


Paper Citation


in Harvard Style

Cyganek B. and Socha Ł. (2006). COMPARISON OF MATCHING STRATEGIES FOR COLOUR IMAGES . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 364-369. DOI: 10.5220/0001369603640369


in Bibtex Style

@conference{visapp06,
author={Bogusław Cyganek and Łukasz Socha},
title={COMPARISON OF MATCHING STRATEGIES FOR COLOUR IMAGES},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={364-369},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001369603640369},
isbn={972-8865-40-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - COMPARISON OF MATCHING STRATEGIES FOR COLOUR IMAGES
SN - 972-8865-40-6
AU - Cyganek B.
AU - Socha Ł.
PY - 2006
SP - 364
EP - 369
DO - 10.5220/0001369603640369