trainf_ocr_class_svm_protected — Train an OCR classifier with data from a (protected) training file.
trainf_ocr_class_svm_protected trains the OCR classifier OCRHandle with the training data stored in the OCR training files given by TrainingFile. Its functionality corresponds to the functionality of trainf_ocr_class_svm, with the addition that trainf_ocr_class_svm_protected can process unprotected and protected training files. Protected training files can be used only with the correct user password Password. If the number of passwords Password equals 1, then every input file TrainingFile is checked with that password, otherwise the number of passwords has to be equal to the number of input files and the input file at position n is checked with the password at position n. For unprotected training files the passwords are ignored.
For a more detailed description of the operator's functionality see trainf_ocr_class_svm. The concept of protecting OCR training data in HALCON is described in protect_ocr_trainf.
This operator modifies the state of the following input parameter:
Handle of the OCR classifier.
Names of the training files.
Default value: 'ocr.trf'
File extension: .trf, .otr
Passwords for protected training files.
Stop parameter for training.
Default value: 0.001
Suggested values: 0.00001, 0.0001, 0.001, 0.01, 0.1
Mode of training.
Default value: 'default'
List of values: 'add_sv_to_train_set', 'default'
If the parameters are valid the operator trainf_ocr_class_svm_protected returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.
trainf_ocr_class_svm_protected may return the error 9211 (Matrix is not positive definite) if Preprocessing = 'canonical_variates' is used. This typically indicates that not enough training samples have been stored for each class. In this case we recommend to change Preprocessing to 'normalization'. Another solution can be to add more training samples.
create_ocr_class_svm, write_ocr_trainf, append_ocr_trainf, write_ocr_trainf_image, protect_ocr_trainf
do_ocr_single_class_svm, do_ocr_multi_class_svm, write_ocr_class_svm