do_ocr_single_class_mlpT_do_ocr_single_class_mlpDoOcrSingleClassMlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlp (Operator)

Name

do_ocr_single_class_mlpT_do_ocr_single_class_mlpDoOcrSingleClassMlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlp — Classify a single character with an OCR classifier.

Signature

Description

do_ocr_single_class_mlpdo_ocr_single_class_mlpDoOcrSingleClassMlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlp computes the best NumNumNumNumNumnum classes of the character given by the region CharacterCharacterCharacterCharacterCharactercharacter and the gray values ImageImageImageImageImageimage with the OCR classifier OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleOCRHandle and returns the classes in ClassClassClassClassClassclassVal and the corresponding confidences (probabilities) of the classes in ConfidenceConfidenceConfidenceConfidenceConfidenceconfidence. Because multiple classes may be returned by do_ocr_single_class_mlpdo_ocr_single_class_mlpDoOcrSingleClassMlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlp, CharacterCharacterCharacterCharacterCharactercharacter may only contain a single region (a single character). If multiple characters should be classified in a single call, do_ocr_multi_class_mlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpDoOcrMultiClassMlp must be used. Because do_ocr_multi_class_mlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpDoOcrMultiClassMlp typically is faster than a loop with do_ocr_single_class_mlpdo_ocr_single_class_mlpDoOcrSingleClassMlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlp and because the confidences can be interpreted as probabilities (see classify_class_mlpclassify_class_mlpClassifyClassMlpclassify_class_mlpClassifyClassMlpClassifyClassMlp and evaluate_class_mlpevaluate_class_mlpEvaluateClassMlpevaluate_class_mlpEvaluateClassMlpEvaluateClassMlp), and it is therefore easy to check whether a character has been classified with too much uncertainty, in most cases do_ocr_multi_class_mlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpDoOcrMultiClassMlp should be used, unless the second-best class should be examined explicitly. Before calling do_ocr_single_class_mlpdo_ocr_single_class_mlpDoOcrSingleClassMlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlp, the classifier must be trained with trainf_ocr_class_mlptrainf_ocr_class_mlpTrainfOcrClassMlptrainf_ocr_class_mlpTrainfOcrClassMlpTrainfOcrClassMlp.

Parallelization

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).
• Multithreading scope: global (may be called from any thread).
• Processed without parallelization.

Parameters

Result

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

Possible Predecessors

trainf_ocr_class_mlptrainf_ocr_class_mlpTrainfOcrClassMlptrainf_ocr_class_mlpTrainfOcrClassMlpTrainfOcrClassMlp, read_ocr_class_mlpread_ocr_class_mlpReadOcrClassMlpread_ocr_class_mlpReadOcrClassMlpReadOcrClassMlp

Alternatives

do_ocr_multi_class_mlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpDoOcrMultiClassMlp

See also

create_ocr_class_mlpcreate_ocr_class_mlpCreateOcrClassMlpcreate_ocr_class_mlpCreateOcrClassMlpCreateOcrClassMlp, classify_class_mlpclassify_class_mlpClassifyClassMlpclassify_class_mlpClassifyClassMlpClassifyClassMlp

Module

OCR/OCV