Visual system for drivers' eye recognition

  • Authors:
  • Bogusław Cyganek;Sławomir Gruszczyński

  • Affiliations:
  • AGH University of Science and Technology, Kraków, Poland;AGH University of Science and Technology, Kraków, Poland

  • Venue:
  • HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part I
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper presents a visual system for human eye recognition for control of driver's fatigue. Modules of the system are organized into a cascade. Processing starts with skin segmentation, followed by the compact skin regions selection obtained with the adaptive window growing technique. Next step consists in selection of candidate regions based on the proposed eye model. The final eye/non-eye classification is done with a classifier build upon the higher order singular value decomposition of the deformable pattern tensor.