SearchPredictor Properties

Correction factors in X and Y direction required to rescale the input images for projection onto the retina.

Radius for extracting positive search instances. The unit size is the size of the feature window, i.e. a value of 0.5 means that positive samples can be extracted from withing a range of +/- Feature Window Width and +/- Feature Window Height around each trained instance. Smaller values will necessitate a finer search grid but may yield better results on difficult search tasks.

Feature resolution to be used for the third and later classification steps.

Feature resolution to be used for the first two classification steps.

The feature window extent that has been used during classifier training.

Name of the file the object has been loaded from (or if the object was not loaded).

Native Manto classifier handle.

The plane count of the images that have been used for generating this classifier. Image on which this classifier is to be used will need to have the same plane count.

Interpolation setting used for generating this object.

Invariances that have been trained on this classifier.

Tests if the native handle has already been disposed.

Regularization value that has been used for generating this object.

The maximum number of results that can be extracted in a GridSearch operation. Increasing this value will increase the amount of memory allocated by this SearchPredictor object.

Number of classification steps defined during training.

Intercept weight that has been used for generating this object.

Preprocessing code with which this object was generated.

Size of the "Retina" in paxels. The retina is the set of paxels onto which the input image is projected using the preprocessing code prior to application/training of the classifier.

Range of angles that was covered during classifier training.

Sample size that has been used in each training set.

Range of scale factors that was covered during classifier training.