do_ocr_word_svmT_do_ocr_word_svmDoOcrWordSvmDoOcrWordSvmdo_ocr_word_svm (Operator)

Name

do_ocr_word_svmT_do_ocr_word_svmDoOcrWordSvmDoOcrWordSvmdo_ocr_word_svm — Classify a related group of characters with an OCR classifier.

Signature

Description

do_ocr_word_svmdo_ocr_word_svmDoOcrWordSvmDoOcrWordSvmDoOcrWordSvmdo_ocr_word_svm works like do_ocr_multi_class_svmdo_ocr_multi_class_svmDoOcrMultiClassSvmDoOcrMultiClassSvmDoOcrMultiClassSvmdo_ocr_multi_class_svm insofar as it computes the best class for each of the characters given by the regions CharacterCharacterCharacterCharactercharactercharacter and the gray values ImageImageImageImageimageimage with the OCR classifier OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleocrhandle, and returns the results in ClassClassClassClassclassValclass.

In contrast to do_ocr_multi_class_svmdo_ocr_multi_class_svmDoOcrMultiClassSvmDoOcrMultiClassSvmDoOcrMultiClassSvmdo_ocr_multi_class_svm, do_ocr_word_svmdo_ocr_word_svmDoOcrWordSvmDoOcrWordSvmDoOcrWordSvmdo_ocr_word_svm treats the group of characters as an entity which yields a WordWordWordWordwordword by concatenating the class names for each character region. This allows to restrict the allowed classification results on a textual level by specifying an ExpressionExpressionExpressionExpressionexpressionexpression describing the expected word.

The ExpressionExpressionExpressionExpressionexpressionexpression may restrict the word to belong to a predefined lexicon created using create_lexiconcreate_lexiconCreateLexiconCreateLexiconCreateLexiconcreate_lexicon or import_lexiconimport_lexiconImportLexiconImportLexiconImportLexiconimport_lexicon, by specifying the name of the lexicon in angular brackets as in '<mylexicon>'"<mylexicon>""<mylexicon>""<mylexicon>""<mylexicon>""<mylexicon>". If the ExpressionExpressionExpressionExpressionexpressionexpression is of any other form, it is interpreted as a regular expression with the same syntax as specified for tuple_regexp_matchtuple_regexp_matchTupleRegexpMatchTupleRegexpMatchTupleRegexpMatchtuple_regexp_match. Note that you will usually want to use an expression of the form '^...$' when using variable quantifiers like '*', to ensure that the entire word is used in the expression. Also note that in contrast to tuple_regexp_matchtuple_regexp_matchTupleRegexpMatchTupleRegexpMatchTupleRegexpMatchtuple_regexp_match, do_ocr_word_svmdo_ocr_word_svmDoOcrWordSvmDoOcrWordSvmDoOcrWordSvmdo_ocr_word_svm does not support passing extra options in an expression tuple.

If the word derived from the best class for each character does not match the ExpressionExpressionExpressionExpressionexpressionexpression, do_ocr_word_svmdo_ocr_word_svmDoOcrWordSvmDoOcrWordSvmDoOcrWordSvmdo_ocr_word_svm attempts to correct it by considering the NumAlternativesNumAlternativesNumAlternativesNumAlternativesnumAlternativesnum_alternatives best classes for each character. The alternatives used are identical to those returned by do_ocr_single_class_svmdo_ocr_single_class_svmDoOcrSingleClassSvmDoOcrSingleClassSvmDoOcrSingleClassSvmdo_ocr_single_class_svm for a single character. It does so by testing all possible corrections for which the classification result is changed for at most NumCorrectionsNumCorrectionsNumCorrectionsNumCorrectionsnumCorrectionsnum_corrections character regions. Note that NumAlternativesNumAlternativesNumAlternativesNumAlternativesnumAlternativesnum_alternatives and NumCorrectionsNumCorrectionsNumCorrectionsNumCorrectionsnumCorrectionsnum_corrections affect the complexity of the algorithm, so that in some cases internal restrictions are made. See the section 'Complexity' below for further information.

In case the ExpressionExpressionExpressionExpressionexpressionexpression is a lexicon and the above procedure did not yield a result, the most similar word in the lexicon is returned as long as it requires less than NumCorrectionsNumCorrectionsNumCorrectionsNumCorrectionsnumCorrectionsnum_corrections edit operations for the correction (see suggest_lexiconsuggest_lexiconSuggestLexiconSuggestLexiconSuggestLexiconsuggest_lexicon).

The resulting word is graded by a ScoreScoreScoreScorescorescore between 0.0 (no correction found) and 1.0 (original word correct). The ScoreScoreScoreScorescorescore is lowered by adding a penalty according to the number of corrected characters and another (minor) penalty depending on how many better classes have been ignored in order to match the ExpressionExpressionExpressionExpressionexpressionexpression:

with num_corr being the actual number of applied corrections and num_alt the total number of discarded alternatives.

Execution Information

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

Parameters

Complexity

The complexity of checking all possible corrections is of magnitude , where a is the number of alternatives, n is the number of character regions, and c is the number of allowed corrections. However, to guard against a near-infinite loop in case of large n, c is internally clipped to 5, 3, or 1 if a*n >= 30, 60, or 90, respectively.

Result

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

Possible Predecessors

trainf_ocr_class_svmtrainf_ocr_class_svmTrainfOcrClassSvmTrainfOcrClassSvmTrainfOcrClassSvmtrainf_ocr_class_svm, read_ocr_class_svmread_ocr_class_svmReadOcrClassSvmReadOcrClassSvmReadOcrClassSvmread_ocr_class_svm

Alternatives

do_ocr_multi_class_svmdo_ocr_multi_class_svmDoOcrMultiClassSvmDoOcrMultiClassSvmDoOcrMultiClassSvmdo_ocr_multi_class_svm

See also

create_ocr_class_svmcreate_ocr_class_svmCreateOcrClassSvmCreateOcrClassSvmCreateOcrClassSvmcreate_ocr_class_svm, classify_class_svmclassify_class_svmClassifyClassSvmClassifyClassSvmClassifyClassSvmclassify_class_svm

Module

OCR/OCV