SymPaD: Symbolic Patch Descriptor

Sinem Aslan, Ceyhun Burak Akgül, Bülent Sankur, Turhan Tunalı

2015

Abstract

We propose a new local image descriptor named SymPaD for image understanding. SymPaD is a probability vector associated with a given image pixel and represents the attachment of the pixel to a previously designed shape repertoire. As such the approach is model-driven. The SymPad descriptor is illumination and rotation invariant, and extremely flexible on extending the repertoire with any parametrically generated geometrical shapes and any desired additional transformation types.

References

  1. Marr, D., 1982. Vision: A computational investigation into the human representation and processing of visual information, Henry Holt and Co. Inc., New York, NY, 2-46.
  2. Koenderink, J. J., 1984. The structure of images. Biological cybernetics, 50(5), 363-370.
  3. Griffin, L. D., 2007. The second order local-imagestructure solid. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(8), 1355-1366.
  4. Lowe, D. G., 1999. Object recognition from local scaleinvariant features. In 7th IEEE international conference on Computer vision, Vol. 2, pp. 1150-1157.
  5. Dalal, N., and Triggs, B., 2005. Histograms of oriented gradients for human detection. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, (Vol. 1, pp. 886-893).
  6. Csurka, G., Dance, C., Fan, L., Willamowski, J., and Bray, C., 2004. Visual categorization with bags of keypoints. In Workshop on statistical learning in computer vision, ECCV (Vol. 1, No. 1-22, pp. 1-2).
  7. Jurie, F., and Triggs, B., 2005. Creating efficient codebooks for visual recognition, In 10th IEEE International Conference on Computer Vision, (1), 604-610.
  8. Crosier, M., and Griffin, L. D., 2010. Using basic image features for texture classification. International Journal of Computer Vision, 88(3), 447-460.
  9. Griffin, L. D., and Lillholm, M., 2007. Feature category systems for 2nd order local image structure induced by natural image statistics and otherwise. In IS&T/SPIE Electronic Imaging, 6492(09). International Society for Optics and Photonics.
  10. Lillholm, M., and Griffin, L. D., 2008. Novel image feature alphabets for object recognition. In ICPR (pp. 1-4).
  11. Newell, A. J., and Griffin, L. D., 2014. Writer identification using oriented Basic Image Features and the Delta encoding. Pattern Recognition, 47(6), 2255-2265.
  12. Aslan, S., Akgül, C. B., and Sankur, B., 2014. Symbolic feature detection for image understanding. In IS&T/SPIE Electronic Imaging (pp. 902406-902406). International Society for Optics and Photonics.
  13. LeCun, Y. A., Bottou, L., Orr, G. B., and Müller, K. R., 2012. Efficient backprop. In Neural networks: Tricks of the trade (pp. 9-48). Springer Berlin Heidelberg.
  14. Griffin, L. D., Lillholm, M., and Nielsen, M., 2004. Natural image profiles are most likely to be step edges. Vision Research, 44(4), 407-421.
  15. Calonder, M., Lepetit, V., Strecha, C., and Fua, P., 2010. Brief: Binary robust independent elementary features. In ECCV 2010 (pp. 778-792).
  16. Muja, M., and Lowe, D. G., 2012. Fast matching of binary features. In 9th IEEE Conference on Computer and Robot Vision, pp. 404-410.
  17. Law, Marc T., Nicolas Thome, and Matthieu Cord, 2014. Bag-of-Words Image Representation: Key Ideas and Further Insight, Fusion in Computer Vision. Springer International Publishing, 29-52.
  18. Shekar, B. H., Holla, K. R., and Kumari, M. S., 2013. KID: Kirsch Directional Features Based Image Descriptor. In Pattern Recognition and Machine Intelligence (pp. 327- 334). Springer Berlin Heidelberg.
Download


Paper Citation


in Harvard Style

Aslan S., Akgül C., Sankur B. and Tunalı T. (2015). SymPaD: Symbolic Patch Descriptor . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 266-271. DOI: 10.5220/0005361802660271


in Bibtex Style

@conference{visapp15,
author={Sinem Aslan and Ceyhun Burak Akgül and Bülent Sankur and Turhan Tunalı},
title={SymPaD: Symbolic Patch Descriptor},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={266-271},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005361802660271},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - SymPaD: Symbolic Patch Descriptor
SN - 978-989-758-089-5
AU - Aslan S.
AU - Akgül C.
AU - Sankur B.
AU - Tunalı T.
PY - 2015
SP - 266
EP - 271
DO - 10.5220/0005361802660271