Evolutive Parametric Approach for Specular Correction in the Dichromatic Reflection Model

  • Authors:
  • Ramón Moreno;Alicia D'Anjou;Manuel Graña

  • Affiliations:
  • Computational Intelligence Group, University of the Basque Country,;Computational Intelligence Group, University of the Basque Country,;Computational Intelligence Group, University of the Basque Country,

  • Venue:
  • HAIS '08 Proceedings of the 3rd international workshop on Hybrid Artificial Intelligence Systems
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Assuming the dichromatic image model we propose a global reduction of specularity effects by means of parametric illumination gradient images obtained by fitting 2D Legendre polynomials to the specular component of the images. Fitting is done applying a (茂戮驴+ μ) Evolution Strategy. The method could be applied to static robotic monitoring in teams of robots, where the illumination gradient image could be computed once and applied to successive frames until the illumination conditions change drastically. The method could be useful for the detection of image regions with different chromatic properties.