ParametricFittingResult¶
- class menpo.fit.fittingresult.ParametricFittingResult(image, lk, parameters=None, weights=None, costs=None, gt_shape=None, error_type='me_norm')[source]¶
Bases: SemiParametricFittingResult
Object that holds the state of a lucas-kanade object before, during and after it has fitted a particular image.
Parameters: image: :class:`menpo.image.masked.MaskedImage` :
The fitted image.
lk: :class:`menpo.aam.fitter.BasicFitter` :
The fitter object used to fitter the image.
weights: ndarray list :
A list containing the weights of the lk object transform per fitting iteration.
Default: None
weights: ndarray list :
A list containing the weights of the lk appearance model per fitting iteration. Note that, some lk objects do not explicitly recover the weights of the appearance model; in this cases weights is None.
Default: None
costs: ndarray list :
A list containing the values of the cost function optimized by the lk object per fitting iteration.
Default: None
error_type: ‘me_norm’, ‘me’ or ‘rmse’, optional. :
Specifies the way in which the error between the fitted and ground truth shapes is to be computed.
Default: ‘me_norm’
- appearance_reconstructions(as_pixels=False)[source]¶
Generates a list containing the appearance reconstruction obtained at each fitting iteration.
Parameters: as_pixels: boolean, optional :
Whether the result is returned as a list of Images or ndarrays.
Default: False
Returns: appearance_reconstructions: :class:`menpo.image.masked.MaskedImage` :
or ndarray list
A list containing the appearance reconstructions obtained at each fitting iteration.
- plot_cost(figure_id=None, new_figure=False, **kwargs)¶
Plots the cost evolution throughout the fitting.
- plot_error(figure_id=None, new_figure=False, **kwargs)¶
Plots the error evolution throughout the fitting.
- view(**kwargs)¶
View the object using the default rendering engine figure handling. For example, the default behaviour for Matplotlib is that all draw commands are applied to the same figure object.
Parameters: kwargs : dict
Passed through to specific rendering engine.
Returns: viewer : Renderer
The renderer instantiated.
- view_appearance_reconstructions(figure_id=None, new_figure=False, channels=None, **kwargs)[source]¶
Displays the appearance recontructions.
- view_error_images(figure_id=None, new_figure=False, channels=None, **kwargs)[source]¶
Displays the error images.
- view_final_fitting(figure_id=None, new_figure=False, **kwargs)¶
Displays the final fitting result.
- view_ground_truth(figure_id=None, new_figure=False, **kwargs)¶
Displays the ground truth annotation.
- view_initialization(figure_id=None, new_figure=False, **kwargs)¶
Displays the initialization from which the fitting started.
- view_new(**kwargs)¶
View the object on a new figure.
Parameters: kwargs : dict
Passed through to specific rendering engine.
Returns: viewer : Renderer
The renderer instantiated.
- view_on(figure_id, **kwargs)¶
View the object on a a specific figure specified by the given id.
Parameters: figure_id : object
A unique identifier for a figure.
kwargs : dict
Passed through to specific rendering engine.
Returns: viewer : Renderer
The renderer instantiated.
- view_warped_images(figure_id=None, new_figure=False, channels=None, **kwargs)[source]¶
Displays the warped images.
- warped_images(as_pixels=False)[source]¶
Generates a list containing the warped images obtained at each fitting iteration.
Parameters: as_pixels: boolean, optional :
Whether the result is returned as a list of Images or ndarrays.
Default: False
Returns: warped_images: :class:`menpo.image.masked.MaskedImage` or ndarray list :
A list containing the warped images obtained at each fitting iteration.
- algorithm¶
Returns the name of the algorithm used by the Fitter.
- error_type¶
Return the type of error.
- errors¶
Returns a list containing the error at each fitting iteration.
- final_cost¶
Returns the value of the cost function at the final iteration.
- final_error¶
Returns the final fitting error.
Type: float
- final_transform¶
Returns the final transform.
- gt_shape¶
Returns the original ground truth shape associated to the image.
- initial_cost¶
Returns the value of the cost function at the first iteration.
- initial_error¶
Returns the initial fitting error.
Type: float
- initial_transform¶
Returns the initial transform from which the fitting started.
- residual¶
Returns the type of residual used by the basic fitter.
- transforms¶
Generates a list containing the transforms obtained at each fitting iteration.