Fast and Accurate Skin Segmentation in Color Images

  • Authors:
  • Affiliations:
  • Venue:
  • CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
  • Year:
  • 2004

Quantified Score

Hi-index 0.01

Visualization

Abstract

We propose a new type of skin segmentation in color imagesespecially developed for applications that require lowresources. In our recent [7] work we made use of the Mahalanobisdistance that proved its value in human skin segmentation.The calculation of the mentioned distance is verycomputational demanding. This is often a drawback to animplementation on critical applications, where speed is important.Robot applications are among this group.We now present a skin segmentation only based in eachpixel color information to determine its class. We need tomake an initial camera calibration and to determine the STspace that we consider skin color.This method is proved effective for most cases of humaninteraction. The present work can be a initial step in any applicationrequiring human interaction or simply for skin detection.