CRF Model
The Binary LN Model described in the bachelor thesis "Maximum Likelihood Learning And Inference In Conditional Random Fields" by Iulian Vlad Serban, University of Copenhagen, 2012.
|
Public Member Functions | |
CRFModel_GraphCut () | |
CRFModel_GraphCut (int imgWidth, int imgHeight, int MAPSTEPS) | |
int_int_vector | EstimateMAP (const double_double_vector Input) |
Constructor that initializes the configuration of the model. Width and Height are set to 1 pixel.
CRFModel_GraphCut::CRFModel_GraphCut | ( | int | imgWidth, |
int | imgHeight, | ||
int | MAPSTEPS | ||
) |
Constructor that initializes the configuration of the model.
imgWidth | Image width in pixels. |
imgHeight | Image height in pixels. |
MAPSTEPS | Maximum number of steps to perform for MAP estimation. This is irrelevant for Graph Cut methods. |
int_int_vector CRFModel_GraphCut::EstimateMAP | ( | const double_double_vector | Input | ) | [virtual] |
Finds the MAP (Maximum Aposterori Estimation) solution using Graph Cut methods.
Input | Input sample. |
Reimplemented from CRF::CRFModel.