EFFICIENT OBJECT DETECTION ROBUST TO RST WITH MINIMAL SET OF EXAMPLES

Sebastien Onis, Henri Sanson, Christophe Garcia, Jean-Luc Dugelay

2008

Abstract

In this paper, we present an object detection approach based on a similarity measure combining cross-correlation and affine deformation. Current object detection systems provide good results, at the expense of requiring a large training database. The use of correlation anables object detection with very small training set but is not robust to the luminosity change and RST (Rotation, Scale, translation) transformation. This paper presents a detection system that first searches the likely positions and scales of the object using image preprocessing and cross-correlation method and secondly, uses a similarity measure based on affine deformation to confirm or not the predetection. We apply our system to face detection and show the improvement in results due to the images preprocessing and the affine deformation.

References

  1. Dugelay, J. L. and Sanson, H. (1995). Differential methods for the identification of 2d and 3d motion models in image sequences. In Signal Processing: Image Communication 7.
  2. Edwards, G. J., Cootes, T. F., and Taylor, C. J. (1999). Advances in active appearance models. In Computer Vision, 1999. INSTICC Press.
  3. Garcia, C. and Delakis, M. (2004). Convolutional face finder, a neural architecture for fast and robust face detection. In IEEE Transactions on pattern analysis and machine intelligence, Vol.26, NO.11.
  4. MacLean, W. J. and Tsotsos, J. K. (2007). Fast pattern recognition using normalized grey-scale correlation in a pyramid image representation. In Machine Vision & Applications.
  5. Santiago-Mozos, R., Leiva-Murillo, J., Perez-Cruz, F., and Artes-Rodriguez, A. (1999). Supervised-pca and svm classifiers for object detection in infrared images. In IEEE Conference on Advanced Video and Signal Based Surveillance.
  6. Sung, K. K. and Poggio, T. (1998). Example-based learning for view based human face detection. In IEEE Transactions on pattern analysis and machine intelligence, Vol.22, NO.1.
  7. Viola, P. and Jones, M. (2001). Robust real-time object detection. In Second International Workshop on Statistical and Computational Theories of Vision - Modeling, Learning and Sampling.
  8. Wakahara, T., Kimura, Y., and Tomono, A. (2001). Affineinvariant recognition of gray-scale characters using global affine transformation correlation. In IEEE Transactions on pattern analysis and machine intelligence, Vol.23, NO.4.
Download


Paper Citation


in Harvard Style

Onis S., Sanson H., Garcia C. and Dugelay J. (2008). EFFICIENT OBJECT DETECTION ROBUST TO RST WITH MINIMAL SET OF EXAMPLES . 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 179-185. DOI: 10.5220/0001083601790185


in Bibtex Style

@conference{visapp08,
author={Sebastien Onis and Henri Sanson and Christophe Garcia and Jean-Luc Dugelay},
title={EFFICIENT OBJECT DETECTION ROBUST TO RST WITH MINIMAL SET OF EXAMPLES},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={179-185},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001083601790185},
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 - EFFICIENT OBJECT DETECTION ROBUST TO RST WITH MINIMAL SET OF EXAMPLES
SN - 978-989-8111-21-0
AU - Onis S.
AU - Sanson H.
AU - Garcia C.
AU - Dugelay J.
PY - 2008
SP - 179
EP - 185
DO - 10.5220/0001083601790185