Segmentation of lip pixels for lip tracker initialisation
Sadeghi, M.
Kittler, J.
Messer, K.
Sch. of Electronics, Comput. & Math., Surrey Univ., Guildford;
This paper appears in: Image Processing, 2001. Proceedings. 2001 International Conference on
Publication Date: 2001
Volume: 1,
On page(s): 50-53 vol.1
Meeting Date: 10/07/2001 - 10/10/2001
Location: Thessaloniki, Greece
ISBN: 0-7803-6725-1
References Cited: 11
INSPEC Accession Number: 7210822
Digital Object Identifier: 10.1109/ICIP.2001.958950
Current Version Published: 2002-08-07
Abstract
We propose a novel image segmentation method for lip tracker
initialisation which is based on a Gaussian mixture model of the pixel
RGB values. The model is built using the predictive validation technique
advocated by Kittler, Messer and Sadeghi (see Second International
Conference on Advances in Pattern Recognition, Brazil, March 2001) which
has been modified to allow modelling with full covariance matrices. A
subsequent grouping of the mixture components provides the basis for a
Bayesian rule labelling of the pixels as lip or non-lip. We test the
proposed method on a database of 145 images and demonstrate that its
accuracy is significantly better than the segmentation obtained by
k-means clustering. Moreover, the proposed method does not require the
number of segments to be specified a priori
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
