Paper Info
Title
Robust face tracking by integration of two separate trackers: Skin color and facial shape
Abstract
This paper proposes a robust face tracking method based on the condensation algorithm that uses skin color and facial shape as observation measures. Two trackers are used for robust tracking: one tracks the skin color regions and the other tracks the facial shape regions. The two trackers are coupled using an importance sampling technique, where the skin color density obtained from the skin color tracker is used as the importance function to generate samples for the shape tracker. The samples of the skin color tracker within the chosen shape region are updated with higher weights. Also, an adaptive color model is used to avoid the effect of illumination change in the skin color tracker. The proposed face tracker performs more robustly than either the skin-color-based tracker or the facial shape-based tracker, given the presence of background clutter and/or illumination changes.
Year
DOI
Venue
2007
10.1016/j.patcog.2007.03.003
Pattern Recognition
Keywords
Field
DocType
importance sampling,face tracking,skin color tracker,condensation,adaptive color model,skin-color-based tracker,robust face tracking,facial shape,skin color,separate tracker,shape tracker,skin color region,illumination change,facial shape-based tracker,skin color density,proposed face tracker,color model
Facial recognition system,Computer vision,BitTorrent tracker,Importance sampling,Pattern recognition,Clutter,Color model,Artificial intelligence,Biometrics,Facial motion capture,Mathematics,Condensation algorithm
Journal
Volume
Issue
ISSN
40
11
Pattern Recognition
Citations 
PageRank 
References 
6
0.65
15
Authors
2
Name
Order
Citations
PageRank
Hyung-Soo Lee113213.10
Daijin Kim21882126.85