Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
DYNA
Print version ISSN 0012-7353On-line version ISSN 2346-2183
Abstract
JARAMILLO, JORGE A.; GONZALEZ, JUAN R. and CASTELLANOS, GERMÁN. MODEL PARAMETERS TUNING USING GA, ON LIP POSTURES RECOGNITION. Dyna rev.fac.nac.minas [online]. 2007, vol.74, n.151, pp.185-194. ISSN 0012-7353.
Here, a lip posture recognition and segmentation system by means of tuning adjustable parameter models, is shown. For segmentation, deformable templates are used, and for feature extraction a variational model of lip contours is implemented. Both models are tuned by canonical genetic algorithms yielding performances up to 86.5% and 76.6% respectively.
Keywords : Genetic Algorithms; Image segmentation; Feature extraction; Pattern classification; Principal component analysis; Singular values descomposition.