create_class_knn — Create a k-nearest neighbors (k-NN) classifier.
create_class_knn creates a k-nearest neighbors (k-NN) data structure.
This can be either used to classify data or to approximately locate
nearest neighbors in a NumDim-dimensional space.
Most of the operators described in Classification/K-Nearest-Neighbor use
the resulting handle KNNHandle.
The k-NN classifies by searching approximately the nearest neighbors and returning their classes as result. With the used approximation, the search time is logarithmically to the number of samples and dimensions.
The dimension of the feature vectors is the only parameter that necessarily
has to be set in NumDim.
This operator returns a handle. Note that the state of an instance of this handle type may be changed by specific operators even though the handle is used as an input parameter by those operators.
NumDim (input_control) number-array → (integer)
Number of dimensions of the feature.
Default: 10
KNNHandle (output_control) class_knn → (handle)
Handle of the k-NN classifier.
If the parameters are valid, the operator create_class_knn
returns the value 2 (
H_MSG_TRUE)
. If necessary, an exception is raised.
add_sample_class_knn,
train_class_knn
create_class_svm,
create_class_mlp
select_feature_set_knn,
read_class_knn
Marius Muja, David G. Lowe: “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration”; International Conference on Computer Vision Theory and Applications (VISAPP 09); 2009.
Foundation