get_features_ocr_class_knnT_get_features_ocr_class_knnGetFeaturesOcrClassKnnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnn (Operator)

Name

get_features_ocr_class_knnT_get_features_ocr_class_knnGetFeaturesOcrClassKnnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnn — Compute the features of a character.

Signature

get_features_ocr_class_knn(Character : : OCRHandle, Transform : Features)

Description

get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnn computes the features of the character given by CharacterCharacterCharacterCharacterCharactercharacter with the k-NN classifier OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleOCRHandle and returns them in FeaturesFeaturesFeaturesFeaturesFeaturesfeatures. In contrast to do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnn and do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnn, the character is passed as a single image object. Hence, before calling get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnn, reduce_domainreduce_domainReduceDomainreduce_domainReduceDomainReduceDomain must typically be called. The parameter TransformTransformTransformTransformTransformtransform determines whether the feature transformation specified with Preprocessing in create_ocr_class_knncreate_ocr_class_knnCreateOcrClassKnncreate_ocr_class_knnCreateOcrClassKnnCreateOcrClassKnn for the classifier should be applied (TransformTransformTransformTransformTransformtransform = 'true'"true""true""true""true""true") or whether the untransformed features should be returned (TransformTransformTransformTransformTransformtransform = 'false'"false""false""false""false""false"). get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnn can be used to inspect the features that are used for the classification.

Parallelization

Multithreading type: reentrant (runs in parallel with non-exclusive operators).
Multithreading scope: global (may be called from any thread).
Processed without parallelization.

Parameters

CharacterCharacterCharacterCharacterCharactercharacter (input_object) singlechannelimage → object (byte / uint2)

Input character.

OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleOCRHandle (input_control) ocr_knn → (integer)

Handle of the k-NN classifier.

TransformTransformTransformTransformTransformtransform (input_control) string → (string)

Should the feature vector be transformed with the preprocessing?

Default value: 'true' "true" "true" "true" "true" "true"

List of values: 'false'"false""false""false""false""false", 'true'"true""true""true""true""true"

FeaturesFeaturesFeaturesFeaturesFeaturesfeatures (output_control) real-array → (real)

Feature vector of the character.

If the parameters are valid, the operator get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnn returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.

Possible Predecessors

trainf_ocr_class_knntrainf_ocr_class_knnTrainfOcrClassKnntrainf_ocr_class_knnTrainfOcrClassKnnTrainfOcrClassKnn

Module

OCR/OCV

Operators