Object Evidence Extraction Using Simple Gabor Features and Statistical Ranking

  • J. -K. Kamarainen
  • J. Ilonen
  • P. Paalanen
  • M. Hamouz
  • H. Kälviäinen
  • J. Kittler
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)

Abstract

Several novel methods based on locally extracted object features and spatial constellation models have recently been introduced for invariant object detection and recognition. The accuracy and reliability of the methods depend on the success of both tasks: evidence extraction and spatial constellation model search. In this study an accurate and efficient method for evidence extraction is introduced. The proposed method is based on simple Gabor features and their statistical ranking.

References

  1. 1.
    Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. IEEE Trans. on Computers 22, 67–92 (1973)CrossRefGoogle Scholar
  2. 2.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. of the Fourth Alvey Vision Conf., pp. 147–151 (1988)Google Scholar
  3. 3.
    Kadir, T.: Scale, Saliency and Scene Description. PhD thesis, Oxford University (2002)Google Scholar
  4. 4.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  5. 5.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (2003)Google Scholar
  6. 6.
    Hamouz, M., Kittler, J., Kamarainen, J.K., Paalanen, P., Kälviäinen, H.: Affine-invariant face detection and localization using GMM-based feature detector and enhanced appearance model. In: Proc. of the 6th Int. Conference on Automatic Face and Gesture Recognition, Seoul, Korea, pp. 67–72 (2004)Google Scholar
  7. 7.
    Kyrki, V., Kamarainen, J.K., Kälviäinen, H.: Simple Gabor feature space for invariant object recognition. Pattern Recognition Letters 25, 311–318 (2003)CrossRefGoogle Scholar
  8. 8.
    Paalanen, P., Kamarainen, J.K., Ilonen, J., Kälviäinen, H.: Feature representation and discrimination based on Gaussian mixture model probability densities – practices and algorithms. Research report 95, Department of Information Technology, Lappeenranta University of Technology (2005)Google Scholar
  9. 9.
    Hamouz, M.: Feature-based affine-invariant detection and localization of faces. PhD thesis, University of Surrey (2004)Google Scholar
  10. 10.
    Kämäräinen, J.K.: Feature Extraction Using Gabor Filters. PhD thesis, Lappeenranta University of Technology (2003)Google Scholar
  11. 11.
    Figueiredo, M., Jain, A.: Unsupervised learning of finite mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 381–396 (2002)CrossRefGoogle Scholar
  12. 12.
    Messer, K., Matas, J., Kittler, J., Luettin, J., Maitre, G.: XM2VTSDB: The extended M2VTS Database. In: Proc. of the 2nd Int. Conf. on Audio and Video-based Biometric Person Authentication, pp. 72–77 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • J. -K. Kamarainen
    • 1
  • J. Ilonen
    • 1
  • P. Paalanen
    • 1
  • M. Hamouz
    • 2
  • H. Kälviäinen
    • 1
  • J. Kittler
    • 2
  1. 1.Dept. of Information TechnologyLappeenranta University of TechnologyFinland
  2. 2.University of SurreyUnited Kingdom

Personalised recommendations