NormalizedCrossCorrelationMean#
- class NormalizedCrossCorrelationMean(**kwargs)[source]#
Bases:
NormalizedCrossCorrelation
Computes a similar score than
NormalizedCrossCorrelation
, but additionally factors in the mean of template and target.\[\text{score} = \frac{(\text{target_weights} - \text{mean(target_weights)}) \cdot (\text{template_weights} - \text{mean(template_weights)})} {\text{max(target_norm} \times \text{template_norm, eps)}}\]Where:
\[\text{target_norm} = ||\text{target_weights} - \text{mean(target_weights)}||\]\[\text{template_norm} = ||\text{template_weights} - \text{mean(template_weights)}||\]Here, \(||.||\) denotes the L2 (Euclidean) norm, and \(\text{mean(.)}\) computes the mean of the respective weights.
- Parameters:
- targetNDArray
A d-dimensional target to match the template coordinate set to.
- template_coordinatesNDArray
Template coordinate array with shape (d,n).
- template_weightsNDArray
Template weight array with shape (n,).
- template_mask_coordinatesNDArray, optional
Template mask coordinates with shape (d,n).
- target_maskNDArray, optional
A d-dimensional mask to be applied to the target.
- negate_scorebool, optional
Whether the final score should be multiplied by negative one. Default is True.
- return_gradientbool, optional
Invoking __call_ returns a tuple of score and parameter gradient. Default is False.
- **kwargsDict, optional
Keyword arguments propagated to downstream functions.
Methods
Calculate the normalized gradient of the cost function w.r.t.
Compute the matching score for the given transformation parameters.
Computes the score after a given rotation.
Computes the score after a given translation.