Convergent stochastic Expectation Maximization algorithm with efficient sampling in high dimension. Application to deformable template model estimation.
Stéphanie AllassonnièreEstelle KuhnPublished in: Comput. Stat. Data Anal. (2015)
Keyphrases
- expectation maximization
- em algorithm
- deformable template
- probabilistic model
- parameter estimation
- bayesian framework
- high dimension
- parametric models
- energy function
- similarity measure
- learning algorithm
- input data
- maximum likelihood
- matching algorithm
- pattern recognition
- graphical models
- least squares
- prior knowledge
- feature vectors
- image segmentation