Face tracking for expressions simulations

  • Authors:
  • Peter Gejgus;Martin Sperka

  • Affiliations:
  • Department of Computer Graphics and Image Processing, Comenius University of Technology;Department of Computer Science and Engineering, Slovak University of Technology

  • Venue:
  • CompSysTech '03 Proceedings of the 4th international conference conference on Computer systems and technologies: e-Learning
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a work that is part of the system for creation of real-faced avatar for emphatic communication. We have made a new extension of the KL T (Kanade-Lucas-Tomasi) face tracker. which is robust against loss of the tracked points. Stochastic skin-color model is used for a face segmentation in the frames contained in a video sequence. Ellipse-fitting is used for selection of the face candidates because of the elliptical face shape. The proposed method achieved real-time performance The results seem very promising.