Skip to content

get_features_ocr_class_mlpGetFeaturesOcrClassMlpGetFeaturesOcrClassMlpget_features_ocr_class_mlpT_get_features_ocr_class_mlp🔗

Short description🔗

get_features_ocr_class_mlpGetFeaturesOcrClassMlpGetFeaturesOcrClassMlpget_features_ocr_class_mlpT_get_features_ocr_class_mlp — Compute the features of a character.

Signature🔗

get_features_ocr_class_mlp( image Character, ocr_mlp OCRHandle, string Transform, out real Features )void GetFeaturesOcrClassMlp( const HObject& Character, const HTuple& OCRHandle, const HTuple& Transform, HTuple* Features )static void HOperatorSet.GetFeaturesOcrClassMlp( HObject character, HTuple OCRHandle, HTuple transform, out HTuple features )def get_features_ocr_class_mlp( character: HObject, ocrhandle: HHandle, transform: str ) -> Sequence[float]

Herror T_get_features_ocr_class_mlp( const Hobject Character, const Htuple OCRHandle, const Htuple Transform, Htuple* Features )

HTuple HImage::GetFeaturesOcrClassMlp( const HOCRMlp& OCRHandle, const HString& Transform ) const

HTuple HImage::GetFeaturesOcrClassMlp( const HOCRMlp& OCRHandle, const char* Transform ) const

HTuple HImage::GetFeaturesOcrClassMlp( const HOCRMlp& OCRHandle, const wchar_t* Transform ) const (Windows only)

HTuple HOCRMlp::GetFeaturesOcrClassMlp( const HImage& Character, const HString& Transform ) const

HTuple HOCRMlp::GetFeaturesOcrClassMlp( const HImage& Character, const char* Transform ) const

HTuple HOCRMlp::GetFeaturesOcrClassMlp( const HImage& Character, const wchar_t* Transform ) const (Windows only)

HTuple HImage.GetFeaturesOcrClassMlp( HOCRMlp OCRHandle, string transform )

HTuple HOCRMlp.GetFeaturesOcrClassMlp( HImage character, string transform )

Description🔗

get_features_ocr_class_mlpGetFeaturesOcrClassMlp computes the features of the character given by Charactercharactercharacter with the OCR classifier OCRHandleOCRHandleocrhandle and returns them in Featuresfeaturesfeatures. In contrast to do_ocr_single_class_mlpDoOcrSingleClassMlp and do_ocr_multi_class_mlpDoOcrMultiClassMlp, the character is passed as a single image object. Hence, before calling get_features_ocr_class_mlpGetFeaturesOcrClassMlp, reduce_domainReduceDomain must typically be called. The parameter Transformtransformtransform determines whether the feature transformation specified with Preprocessingpreprocessingpreprocessing in create_ocr_class_mlpCreateOcrClassMlp for the classifier should be applied (Transformtransformtransform \(=\) 'true'"true") or whether the untransformed features should be returned (Transformtransformtransform \(=\) 'false'"false"). get_features_ocr_class_mlpGetFeaturesOcrClassMlp can be used to inspect the features that are used for the classification.

Execution information🔗

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🔗

Charactercharactercharacter (input_object) singlechannelimage → object (byte / uint2)HObject (byte / uint2)HImage (byte / uint2)HObject (byte / uint2)Hobject (byte / uint2)

Input character.

OCRHandleOCRHandleocrhandle (input_control) ocr_mlp → (handle)HTuple (HHandle)HOCRMlp, HTuple (IntPtr)HHandleHtuple (handle)

Handle of the OCR classifier.

Transformtransformtransform (input_control) string → (string)HTuple (HString)HTuple (string)strHtuple (char*)

Should the feature vector be transformed with the preprocessing?

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

Featuresfeaturesfeatures (output_control) real-array → (real)HTuple (double)HTuple (double)Sequence[float]Htuple (double)

Feature vector of the character.

Result🔗

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

Combinations with other operators🔗

Combinations

Possible predecessors

trainf_ocr_class_mlpTrainfOcrClassMlp

See also

create_ocr_class_mlpCreateOcrClassMlp

Module🔗

OCR/OCV