Skin-Color Extraction in Images with Complex Background and Varying Illumination

  • Authors:
  • Quan Huynh-Thu;Mitsuhiko Meguro;Masahide Kaneko

  • Affiliations:
  • -;-;-

  • Venue:
  • WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

A skin-color extraction algorithm is proposed to detecthuman faces in color images with varying illumination conditionand presence of complex background. The approachis based on both a Gaussian mixture model of human skincolordistribution and image segmentation using an automaticand adaptive multi-thresholding technique. Detectedregions are then refined by morphological operations.Experimental results on images presenting a widerange of variations in lighting condition, face orientation,scale, pose, facial expression and background, demonstratethe efficiency of our skin-segmentation algorithm. Usingadditional information about facial features, our methodbecomes an efficient step in localizing candidate faces fora face detection system.