trainf_ocr_class_box — Train an OCR classifier with the help of a training file.
trainf_ocr_class_box is obsolete and is only provided for
reasons of backward compatibility. New applications should use the
MLP, SVM or CNN based operators instead.
trainf_ocr_class_box( : : OcrHandle, TrainingFile : AvgConfidence)
The operator trainf_ocr_class_box trains the classifier
OcrHandle via the indicated training files.
Any number of files can be indicated. The parameter AvgConfidence
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 OcrHandle are discarded.
The names of the characters in the file must fit the network.
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.
OcrHandle (input_control, state is modified) ocr_box → (handle)
ID of the desired OCR-network.
TrainingFile (input_control) filename.read(-array) → (string)
Names of the training files.
Default value: 'train_ocr'
File extension: .trf, .otr
AvgConfidence (output_control) real → (real)
Average confidence during a re-classification of the trained characters.
If the file name is correct and the data fit the network,
the operator trainf_ocr_class_box returns the value
2 (H_MSG_TRUE).
Otherwise an exception will be raised.
create_ocr_class_box,
read_ocr
traind_ocr_class_box,
write_ocr,
do_ocr_multi,
do_ocr_single
OCR/OCV