Face recognition via direct search optimized Gabor filters

  • Authors:
  • Cătălin-Daniel Căleanu;Vasile Gui;Florin Alexa

  • Affiliations:
  • Applied Electronics, University POLITEHNICA Timişoara, Timişoara, România;Communications, University POLITEHNICA Timişoara, Timişoara, România;Communications, University POLITEHNICA Timişoara, Timişoara, România

  • Venue:
  • ICOSSE'06 Proceedings of the 5th WSEAS international conference on System science and simulation in engineering
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

While Gabor filter banks are one of the most successful image processing techniques for face processing tasks, finding which frequency and orientation bands are responsible for the success of the approach is still an open topic. This paper introduces the Mesh Adaptive Direct Search (MADS) algorithm for the Gabor filters frequency and orientation optimization. In this paper MADS optimization has been applied in the context of face recognition. Compared to heuristic or trial and error parameters selection, the proposed method possesses a number of advantages; among the most important of them is the higher recognition accuracy obtained on public face databases.