Skip to content

trainf_ocr_class_boxTrainfOcrClassBoxTrainfOcrClassBoxtrainf_ocr_class_boxT_trainf_ocr_class_box🔗

Short description🔗

trainf_ocr_class_boxTrainfOcrClassBoxTrainfOcrClassBoxtrainf_ocr_class_boxT_trainf_ocr_class_box — Train an OCR classifier with the help of a training file.

Warning🔗

trainf_ocr_class_boxTrainfOcrClassBox is obsolete and is only provided for reasons of backward compatibility. New applications should use the MLP, SVM or CNN based operators instead.

Signature🔗

trainf_ocr_class_box( ocr_box OcrHandle, filename.read TrainingFile, out real AvgConfidence )void TrainfOcrClassBox( const HTuple& OcrHandle, const HTuple& TrainingFile, HTuple* AvgConfidence )static void HOperatorSet.TrainfOcrClassBox( HTuple ocrHandle, HTuple trainingFile, out HTuple avgConfidence )def trainf_ocr_class_box( ocr_handle: HHandle, training_file: MaybeSequence[str] ) -> float

Herror T_trainf_ocr_class_box( const Htuple OcrHandle, const Htuple TrainingFile, Htuple* AvgConfidence )

double HOCRBox::TrainfOcrClassBox( const HTuple& TrainingFile ) const

double HOCRBox::TrainfOcrClassBox( const HString& TrainingFile ) const

double HOCRBox::TrainfOcrClassBox( const char* TrainingFile ) const

double HOCRBox::TrainfOcrClassBox( const wchar_t* TrainingFile ) const (Windows only)

double HOCRBox.TrainfOcrClassBox( HTuple trainingFile )

double HOCRBox.TrainfOcrClassBox( string trainingFile )

Description🔗

The operator trainf_ocr_class_boxTrainfOcrClassBox trains the classifier OcrHandleocrHandleocr_handle via the indicated training files. Any number of files can be indicated. The parameter AvgConfidenceavgConfidenceavg_confidence provides information about the success of the training: It contains the average confidence of the trained characters measured by a re-classification. The confidence of mismatched characters is set to 0 (thus, the average confidence will be decreased significantly). Please, note that training characters that have no corresponding class in the classifier OcrHandleocrHandleocr_handle are discarded.

Attention🔗

The names of the characters in the file must fit the network.

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.

This operator modifies the state of the following input parameter:

During execution of this operator, access to the value of this parameter must be synchronized if it is used across multiple threads.

Parameters🔗

OcrHandleocrHandleocr_handle (input_control, state is modified) ocr_box → (handle)HTuple (HHandle)HOCRBox, HTuple (IntPtr)HHandleHtuple (handle)

ID of the desired OCR-network.

TrainingFiletrainingFiletraining_file (input_control) filename.read(-array) → (string)HTuple (HString)HTuple (string)MaybeSequence[str]Htuple (char*)

Names of the training files.

Default: 'train_ocr'"train_ocr"
File extension: .trf, .otr

AvgConfidenceavgConfidenceavg_confidence (output_control) real → (real)HTuple (double)HTuple (double)floatHtuple (double)

Average confidence during a re-classification of the trained characters.

Example🔗

(C)

HTuple  TrainingFile, OcrHandle, AvgConfidence\;
T_create_ocr_class_box(WidthPattern,HeightPattern,Interpolation,
                    Features,\Character,&OcrHandle)\;
create_tuple(&TrainingFile,2)\;
set_s(TrainingFile,"data1",0)\;
set_s(TrainingFile,"data2",1)\;
T_trainf_ocr_class_box(OcrHandle,TrainingFile,&AvgConfidence)\;

Result🔗

If the file name is correct and the data fit the network, the operator trainf_ocr_class_boxTrainfOcrClassBox returns the value 2 (H_MSG_TRUE). Otherwise an exception will be raised.

Combinations with other operators🔗

Combinations

Possible predecessors

create_ocr_class_boxCreateOcrClassBox, read_ocrReadOcr

Possible successors

traind_ocr_class_boxTraindOcrClassBox, write_ocrWriteOcr, do_ocr_multiDoOcrMulti, do_ocr_singleDoOcrSingle

Alternatives

traind_ocr_class_boxTraindOcrClassBox

Module🔗

OCR/OCV