get_features_ocr_class_knnT_get_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn (Operator)
Name
get_features_ocr_class_knnT_get_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn — Compute the features of a character.
Signature
Description
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn computes the features of the
character given by CharacterCharacterCharactercharactercharacter with the k-NN classifier
OCRHandleOCRHandleOCRHandleOCRHandleocrhandle and returns them in FeaturesFeaturesFeaturesfeaturesfeatures. In
contrast to do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knn and
do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnndo_ocr_multi_class_knn, the character is passed as a single
image object. Hence, before calling
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn, reduce_domainreduce_domainReduceDomainReduceDomainreduce_domain must
typically be called. The parameter TransformTransformTransformtransformtransform determines
whether the feature transformation specified with
PreprocessingPreprocessingPreprocessingpreprocessingpreprocessing in create_ocr_class_knncreate_ocr_class_knnCreateOcrClassKnnCreateOcrClassKnncreate_ocr_class_knn for the
classifier should be applied (TransformTransformTransformtransformtransform =
'true'"true""true""true""true") or whether the untransformed features should be
returned (TransformTransformTransformtransformtransform = 'false'"false""false""false""false").
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn can be used to inspect the
features that are used for the classification.
Execution Information
- Multithreading type: reentrant (runs in parallel with non-exclusive operators).
- Multithreading scope: global (may be called from any thread).
- Processed without parallelization.
Parameters
CharacterCharacterCharactercharactercharacter (input_object) singlechannelimage → objectHImageHObjectHObjectHobject (byte / uint2)
Input character.
OCRHandleOCRHandleOCRHandleOCRHandleocrhandle (input_control) ocr_knn → HOCRKnn, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of the k-NN classifier.
TransformTransformTransformtransformtransform (input_control) string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)
Should the feature vector be transformed with
the preprocessing?
Default:
'true'
"true"
"true"
"true"
"true"
List of values:
'false'"false""false""false""false", 'true'"true""true""true""true"
FeaturesFeaturesFeaturesfeaturesfeatures (output_control) real-array → HTupleSequence[float]HTupleHtuple (real) (double) (double) (double)
Feature vector of the character.
Result
If the parameters are valid, the operator
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn returns the value 2 (
H_MSG_TRUE)
. If
necessary, an exception is raised.
Possible Predecessors
trainf_ocr_class_knntrainf_ocr_class_knnTrainfOcrClassKnnTrainfOcrClassKnntrainf_ocr_class_knn
See also
create_ocr_class_knncreate_ocr_class_knnCreateOcrClassKnnCreateOcrClassKnncreate_ocr_class_knn
Module
OCR/OCV