The Performance of the Haar Cascade Classifiers Applied to the Face and Eyes Detection

  • Adam Schmidt
  • Andrzej Kasiński
Part of the Advances in Soft Computing book series (AINSC, volume 45)


Recently we have presented the hierarchical face and eye detection system based on Haar Cascade Classifiers. In this paper we focus on the optimization of detectors training. Moreover, we compare the performance of Lienhart’s face detectors [1] and Castrillon-Santana’s eyes detectors [2] with those which have been trained by us.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lienhart R, Kuranov A, Pisarevsky V (2002) Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection. Technical report, Microprocessor Research Lab, Intel LabsGoogle Scholar
  2. 2.
    Castrillón-Santana M, Lorenzo-Navarro J, Déniz-Suárez O and Falcón-Martel A (2005) Multiple face detection at different resolutions for perceptual user interfaces. In: 2nd ICPRIA. Estoril, PortugalGoogle Scholar
  3. 3.
    Campadelli P, Lanzarotti R, Lipori G (2006 (preprint)) Eye localization: a survey. In: The fundamentals of verbal and non verbal communication and the biometrical issues. NATO Science SeriesGoogle Scholar
  4. 4.
    Kasinski A, Schmidt A (2007) The Architecture of the Face and Eyes Detection System Based on Cascade Classifiers. Submitted to CORES 2007Google Scholar
  5. 5.
    Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: Proceedings of CVPR 1:511–518Google Scholar
  6. 6.
    The Open Computer Vision Library, Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Adam Schmidt
    • 1
  • Andrzej Kasiński
    • 1
  1. 1.Institute of Control and Information EngineeringPoznanPoland

Personalised recommendations