Comparison of Genetic-based Feature Extraction Methods for Facial Recognition

  title={Comparison of Genetic-based Feature Extraction Methods for Facial Recognition},
  author={Joseph Shelton and Gerry V. Dozier and Kelvin S. Bryant and Lasanio Small and Joshua Adams and Khary Popplewell and Tamirat Abegaz and Damon L. Woodard and Karl Ricanek},
In previous research, Shelton et al. presented a geneticbased method for evolving feature extractors for facial recognition. The technique presented evolved feature extractors that consisted of non-uniform, overlapping patches and did not cover the entire image. In this paper, we compare the use of non-uniform, overlapping patches with uniform, overlapping patches. Our results show a statistically significant performance improvement over the technique presented in Shelton’s previous paper. 

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.

An Introduction To Multibiometrics

  • Arun Ross
  • Appeared in Proc. of the 15 European Signal…
  • 2007
1 Excerpt

Pietikinen, "Face Description with Local Binary Patterns: Application to Face Recognition,

  • Timo Ahonen, Abdenour Hadid, Matti
  • IEEE Transactions on Pattern Analysis and Machine…
  • 2006

Overview of face recognition grand challenge

  • P. J. Flynn P. J. Phillips, T. Scruggs, +5 authors W. Worek
  • IEEE Conference on Computer Vision and Pattern…
  • 2005

and W

  • P. J. Phillips, P. J. Flynn, +5 authors J. Min
  • Worek, “Overview of face recognition grand…
  • 2005
1 Excerpt

Similar Papers

Loading similar papers…