Combination of manual and non-manual features for sign language recognition based on conditional random field and active appearance model.
Hee-Deok YangSeong-Whan LeePublished in: ICMLC (2011)
Keyphrases
- conditional random fields
- sign language recognition
- crf model
- active appearance models
- feature extraction
- generative model
- probabilistic model
- pairwise
- graphical models
- feature vectors
- computer vision
- segmentation method
- spatial information
- higher order
- appearance model
- hidden markov models
- training set
- bayesian networks
- image segmentation