A NEW APPROACH FOR DETECTING LOCAL FEATURES

Giang Phuong Nguyen, Hans Jørgen Andersen

2010

Abstract

Local features up to now are often mentioned in the meaning of interest points. A patch around each point is formed to compute descriptors or feature vectors. Therefore, in order to satisfy different invariant imaging conditions such as scales and viewpoints, an input image is often represented in a scale-space, i.e. size of patches are defined by their corresponding scales. Our proposed technique for detecting local features is different, where no scale-space is required, 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 demonstrate that the triangular representation of images provide invariant features of the image. Experiments using these features show higher retrieval performance over existing methods.

References

  1. Brown, M. and Lowe, D. (2007). Automatic panoramic image stitching using invariant features. International Journal of Computer Vision, 74(1):59-73.
  2. 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.
  3. Distasi, R., Nappi, M., and Vitulano, S. (1997). Image compression by B-Tree triangular coding. IEEE Transactions on Communications, 45(9):1095-1100.
  4. Geusbroek, J., Boomgaard, R., and Smeulders, A. (2001). Color invariance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(12):1338-1350.
  5. Gevers, T. and Smeulders, A. (1999). Color based object recognition. Pattern Recognition, 32:453-464.
  6. Gevers, T., Weijer, J., and Stokman, H. (2006). Color feature detection. Color Image Processing: Methods and Applications, editors R. Lukac and K.N. Plataniotis, CRC Press.
  7. Harris, C. and Stephens, M. (1988). A combined corner and edge detector. Proceedings of the Alvey Vision Conference, pages 147-151.
  8. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60(2):91-110.
  9. Mikolajczyk, K. and Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis & Machine Intelligence, 27(10):1615-1630.
  10. Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., and Van-Gool, L. (2005). A comparison of affine region detectors. International Journal of Computer Vision, 1/2(65):43- 72.
  11. 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.
  12. Niblack, W. (1985). An introduction to digital image processing. Strandberg Publishing Company, Birkeroed, Denmark, Denmark.
  13. Tuytelaars, T. and Mikolajczyk, K. (2008). Local invariant feature detectors. Foundations and Trends in Computer Graphics and Vision, 3(3):177-280.
Download


Paper Citation


in Harvard Style

Phuong Nguyen G. and Jørgen Andersen H. (2010). A NEW APPROACH FOR DETECTING LOCAL FEATURES . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 221-226. DOI: 10.5220/0002848402210226


in Bibtex Style

@conference{visapp10,
author={Giang Phuong Nguyen and Hans Jørgen Andersen},
title={A NEW APPROACH FOR DETECTING LOCAL FEATURES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={221-226},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002848402210226},
isbn={978-989-674-029-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - A NEW APPROACH FOR DETECTING LOCAL FEATURES
SN - 978-989-674-029-0
AU - Phuong Nguyen G.
AU - Jørgen Andersen H.
PY - 2010
SP - 221
EP - 226
DO - 10.5220/0002848402210226