trainf_ocr_class_mlp_protectedT_trainf_ocr_class_mlp_protectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedtrainf_ocr_class_mlp_protected (算子)
名称
trainf_ocr_class_mlp_protectedT_trainf_ocr_class_mlp_protectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedtrainf_ocr_class_mlp_protected — 使用（受保护的）训练文件中的数据训练 OCR 分类器。
签名
void TrainfOcrClassMlpProtected(const HTuple& OCRHandle, const HTuple& TrainingFile, const HTuple& Password, const HTuple& MaxIterations, const HTuple& WeightTolerance, const HTuple& ErrorTolerance, HTuple* Error, HTuple* ErrorLog)
double HOCRMlp::TrainfOcrClassMlpProtected(const HTuple& TrainingFile, const HTuple& Password, Hlong MaxIterations, double WeightTolerance, double ErrorTolerance, HTuple* ErrorLog) const
double HOCRMlp::TrainfOcrClassMlpProtected(const HString& TrainingFile, const HString& Password, Hlong MaxIterations, double WeightTolerance, double ErrorTolerance, HTuple* ErrorLog) const
double HOCRMlp::TrainfOcrClassMlpProtected(const char* TrainingFile, const char* Password, Hlong MaxIterations, double WeightTolerance, double ErrorTolerance, HTuple* ErrorLog) const
double HOCRMlp::TrainfOcrClassMlpProtected(const wchar_t* TrainingFile, const wchar_t* Password, Hlong MaxIterations, double WeightTolerance, double ErrorTolerance, HTuple* ErrorLog) const
(
Windows only)
static void HOperatorSet.TrainfOcrClassMlpProtected(HTuple OCRHandle, HTuple trainingFile, HTuple password, HTuple maxIterations, HTuple weightTolerance, HTuple errorTolerance, out HTuple error, out HTuple errorLog)
double HOCRMlp.TrainfOcrClassMlpProtected(HTuple trainingFile, HTuple password, int maxIterations, double weightTolerance, double errorTolerance, out HTuple errorLog)
double HOCRMlp.TrainfOcrClassMlpProtected(string trainingFile, string password, int maxIterations, double weightTolerance, double errorTolerance, out HTuple errorLog)
描述
trainf_ocr_class_mlp_protectedtrainf_ocr_class_mlp_protectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedtrainf_ocr_class_mlp_protected trains the OCR classifier
OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleocrhandle with the training data stored in the OCR
training files given by TrainingFileTrainingFileTrainingFileTrainingFiletrainingFiletraining_file. Its functionality
corresponds to the functionality of trainf_ocr_class_mlptrainf_ocr_class_mlpTrainfOcrClassMlpTrainfOcrClassMlpTrainfOcrClassMlptrainf_ocr_class_mlp,
with the addition that trainf_ocr_class_mlp_protectedtrainf_ocr_class_mlp_protectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedtrainf_ocr_class_mlp_protected
can process unprotected and protected training files. Protected
training files can be used only with the correct user password
PasswordPasswordPasswordPasswordpasswordpassword. If the number of passwords PasswordPasswordPasswordPasswordpasswordpassword
equals 1, then every input file TrainingFileTrainingFileTrainingFileTrainingFiletrainingFiletraining_file 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_mlptrainf_ocr_class_mlpTrainfOcrClassMlpTrainfOcrClassMlpTrainfOcrClassMlptrainf_ocr_class_mlp。The concept of protecting OCR training
data in HALCON is described in protect_ocr_trainfprotect_ocr_trainfProtectOcrTrainfProtectOcrTrainfProtectOcrTrainfprotect_ocr_trainf。
执行信息
- 多线程类型：可重入（与非独占算子并行运行）。
- 多线程作用域：全局（可从任何线程调用）。
- 在内部数据级别上自动并行化。
此算子修改后续输入参数的状态：
在执行此算子时，若该参数值需在多个线程间使用，则必须对其访问进行同步。
参数
OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleocrhandle (输入控制，状态被修改) ocr_mlp → HOCRMlp, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of the OCR classifier.
TrainingFileTrainingFileTrainingFileTrainingFiletrainingFiletraining_file (输入控制) filename.read(-array) → HTupleMaybeSequence[str]HTupleHtuple (string) (string) (HString) (char*)
Names of the training files.
默认值：
'ocr.trf'
"ocr.trf"
"ocr.trf"
"ocr.trf"
"ocr.trf"
"ocr.trf"
File extension:
.trf, .otr
PasswordPasswordPasswordPasswordpasswordpassword (输入控制) string(-array) → HTupleMaybeSequence[str]HTupleHtuple (string) (string) (HString) (char*)
Passwords for protected training files.
MaxIterationsMaxIterationsMaxIterationsMaxIterationsmaxIterationsmax_iterations (输入控制) integer → HTupleintHTupleHtuple (integer) (int / long) (Hlong) (Hlong)
Maximum number of iterations of the
optimization algorithm.
默认值：
200
建议值：
20, 40, 60, 80, 100, 120, 140, 160, 180, 200, 220, 240, 260, 280, 300
WeightToleranceWeightToleranceWeightToleranceWeightToleranceweightToleranceweight_tolerance (输入控制) real → HTuplefloatHTupleHtuple (real) (double) (double) (double)
Threshold for the difference of the weights of
the MLP between two iterations of the
optimization algorithm.
默认值：
1.0
建议值：
1.0, 0.1, 0.01, 0.001, 0.0001, 0.00001
限制：
WeightTolerance >= 1.0e-8
ErrorToleranceErrorToleranceErrorToleranceErrorToleranceerrorToleranceerror_tolerance (输入控制) real → HTuplefloatHTupleHtuple (real) (double) (double) (double)
Threshold for the difference of the mean error
of the MLP on the training data between two
iterations of the optimization algorithm.
默认值：
0.01
建议值：
1.0, 0.1, 0.01, 0.001, 0.0001, 0.00001
限制：
ErrorTolerance >= 1.0e-8
ErrorErrorErrorErrorerrorerror (输出控制) real → HTuplefloatHTupleHtuple (real) (double) (double) (double)
Mean error of the MLP on the training data.
ErrorLogErrorLogErrorLogErrorLogerrorLogerror_log (输出控制) real-array → HTupleSequence[float]HTupleHtuple (real) (double) (double) (double)
Mean error of the MLP on the training data as a
function of the number of iterations of the
optimization algorithm.
结果
如果参数有效，算子
trainf_ocr_class_mlp_protectedtrainf_ocr_class_mlp_protectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedtrainf_ocr_class_mlp_protected 返回值 2 ( H_MSG_TRUE )。如有必要，则抛出异常。
trainf_ocr_class_mlp_protectedtrainf_ocr_class_mlp_protectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedTrainfOcrClassMlpProtectedtrainf_ocr_class_mlp_protected may return the error 9211 (Matrix is
not positive definite) if PreprocessingPreprocessingPreprocessingPreprocessingpreprocessingpreprocessing =
'canonical_variates'"canonical_variates""canonical_variates""canonical_variates""canonical_variates""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 PreprocessingPreprocessingPreprocessingPreprocessingpreprocessingpreprocessing to
'normalization'"normalization""normalization""normalization""normalization""normalization". Another solution can be to add more
training samples.
可能的前趋
create_ocr_class_mlpcreate_ocr_class_mlpCreateOcrClassMlpCreateOcrClassMlpCreateOcrClassMlpcreate_ocr_class_mlp,
write_ocr_trainfwrite_ocr_trainfWriteOcrTrainfWriteOcrTrainfWriteOcrTrainfwrite_ocr_trainf,
append_ocr_trainfappend_ocr_trainfAppendOcrTrainfAppendOcrTrainfAppendOcrTrainfappend_ocr_trainf,
write_ocr_trainf_imagewrite_ocr_trainf_imageWriteOcrTrainfImageWriteOcrTrainfImageWriteOcrTrainfImagewrite_ocr_trainf_image,
protect_ocr_trainfprotect_ocr_trainfProtectOcrTrainfProtectOcrTrainfProtectOcrTrainfprotect_ocr_trainf
可能的后继
do_ocr_single_class_mlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlpDoOcrSingleClassMlpdo_ocr_single_class_mlp,
do_ocr_multi_class_mlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpDoOcrMultiClassMlpDoOcrMultiClassMlpdo_ocr_multi_class_mlp,
write_ocr_class_mlpwrite_ocr_class_mlpWriteOcrClassMlpWriteOcrClassMlpWriteOcrClassMlpwrite_ocr_class_mlp
替代
read_ocr_class_mlpread_ocr_class_mlpReadOcrClassMlpReadOcrClassMlpReadOcrClassMlpread_ocr_class_mlp
另见
trainf_ocr_class_mlptrainf_ocr_class_mlpTrainfOcrClassMlpTrainfOcrClassMlpTrainfOcrClassMlptrainf_ocr_class_mlp,
train_class_mlptrain_class_mlpTrainClassMlpTrainClassMlpTrainClassMlptrain_class_mlp
模块
光学字符识别/光学字符验证