AN ALTERNATIVE TO SCALE-SPACE REPRESENTATION FOR EXTRACTING LOCAL FEATURES IN IMAGE RECOGNITION

Hans Jørgen Andersen, Giang Phuong Nguyen

Abstract

In image recognition, the common approach for extracting local features using a scale-space representation has usually three main steps; first interest points are extracted at different scales, next from a patch around each interest point the rotation is calculated with corresponding orientation and compensation, and finally a descriptor is computed for the derived patch (i.e. feature of the patch). To avoid the memory and computational intensive process of constructing the scale-space, we use a method where no scale-space is required This is done by dividing the given image into a number of triangles with sizes dependent on the content of the image, at the location of each triangle. In this paper, we will demonstrate that by rotation of the interest regions at the triangles it is possible in grey scale images to achieve a recognition precision comparable with that of MOPS. The test of the proposed method is performed on two data sets of buildings.

References

  1. Brown, M., Szeliski, R., and Winder, S. (2005). Multiimage matching using multi-scale oriented patches. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, volume 1, pages 510- 517.
  2. Distasi, R., Nappi, M., and Vitulano, S. (1997). Image compression by B-Tree triangular coding. IEEE Transactions on Communications, 45(9):1095-1100.
  3. Harris, C. and Stephens, M. (1988). A combined corner and edge detector. Proceedings of the Alvey Vision Conference, pages 147-151.
  4. Huang, S., Cai, C., Zhang, Y., He, D. J., and Zhang, Y. (2009). An efficient wood image retrieval using surf descriptor. 2009 International Conference on Test and Measurement, 2:5558.
  5. Koeck, J., Li, F., and Yang, X. (2005). Global localization and relative positioning based on scale-invariant keypoints. Robotics and Autonomous Systems, 52(1):27 - 38.
  6. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60(2):91-110.
  7. Mikolajczyk, K. and Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis & Machine Intelligence, 27(10):1615-1630.
  8. Nguyen, G. and Andersen, H. (2008). Urban building recognition during significant temporal variations. In Proceedings of the IEEE Workshop on Applications of Computer Vision, pages 1-6.
  9. Nguyen, G. P. and Andersen, H. J. (2010). A new approach for detecting local features. In International Conference on Computer Vision Theory and Applications, pages 1-6. Institute for Systems and Technologies of Information, Control and Communication.
  10. Shao, H., Svoboda, T., and Gool, L. V. (2003). Zubud zurich buildings database for image based recognition.
  11. Tuytelaars, T. and Mikolajczyk, K. (2008). Local invariant feature detectors. Foundations and Trends in Computer Graphics and Vision, 3(3):177-280.
  12. Zhi, L. J., Zhang, S. M., Zhao, D. Z., Zhao, H., and Lin, S. K. (2009). Medical image retrieval using sift feature. In Proceedings of the 2009 2nd International Congress on Image and Signal Processing CISP09.
  13. Zhou, H., Yuan, Y., and Shi, C. (2009). Object tracking using sift features and mean shift. Computer Vision and Image Understanding, 113(3):345 - 352.
Download


Paper Citation


in Harvard Style

Jørgen Andersen H. and Phuong Nguyen G. (2012). AN ALTERNATIVE TO SCALE-SPACE REPRESENTATION FOR EXTRACTING LOCAL FEATURES IN IMAGE RECOGNITION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 341-345. DOI: 10.5220/0003836203410345


in Bibtex Style

@conference{visapp12,
author={Hans Jørgen Andersen and Giang Phuong Nguyen},
title={AN ALTERNATIVE TO SCALE-SPACE REPRESENTATION FOR EXTRACTING LOCAL FEATURES IN IMAGE RECOGNITION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={341-345},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003836203410345},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - AN ALTERNATIVE TO SCALE-SPACE REPRESENTATION FOR EXTRACTING LOCAL FEATURES IN IMAGE RECOGNITION
SN - 978-989-8565-03-7
AU - Jørgen Andersen H.
AU - Phuong Nguyen G.
PY - 2012
SP - 341
EP - 345
DO - 10.5220/0003836203410345