do_ocr_word_knndo_ocr_word_knnDoOcrWordKnndo_ocr_word_knnDoOcrWordKnnDoOcrWordKnn (Operator)

Name

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

Signature

Description

do_ocr_word_knndo_ocr_word_knnDoOcrWordKnndo_ocr_word_knnDoOcrWordKnnDoOcrWordKnn works like do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnn 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 classes in ClassClassClassClassClassclassVal and the corresponding confidences of the classes in ConfidenceConfidenceConfidenceConfidenceConfidenceconfidence. The confidences lie between 0.0 and 1.0. The larger the value, the more reliable is the classification of the single characters.

In contrast to do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnn, do_ocr_word_knndo_ocr_word_knnDoOcrWordKnndo_ocr_word_knnDoOcrWordKnnDoOcrWordKnn 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_lexiconCreateLexiconcreate_lexiconCreateLexiconCreateLexicon or import_lexiconimport_lexiconImportLexiconimport_lexiconImportLexiconImportLexicon, 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_matchTupleRegexpMatchtuple_regexp_matchTupleRegexpMatchTupleRegexpMatch. 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_matchTupleRegexpMatchtuple_regexp_matchTupleRegexpMatchTupleRegexpMatch, do_ocr_word_knndo_ocr_word_knnDoOcrWordKnndo_ocr_word_knnDoOcrWordKnnDoOcrWordKnn 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_knndo_ocr_word_knnDoOcrWordKnndo_ocr_word_knnDoOcrWordKnnDoOcrWordKnn attempts to correct it by considering the NumAlternativesNumAlternativesNumAlternativesNumAlternativesNumAlternativesnumAlternatives best classes for each character. The alternatives used are identical to those returned by do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnn for a single character. It does so by testing all possible corrections for which the classification result is changed for at most NumCorrectionsNumCorrectionsNumCorrectionsNumCorrectionsNumCorrectionsnumCorrections character regions.

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 NumCorrectionsNumCorrectionsNumCorrectionsNumCorrectionsNumCorrectionsnumCorrections edit operations for the correction (see suggest_lexiconsuggest_lexiconSuggestLexiconsuggest_lexiconSuggestLexiconSuggestLexicon).

The resulting word is graded by a ScoreScoreScoreScoreScorescore between 0.0 (no correction found) and 1.0 (original word correct), which is determined by the number of corrected characters but also adds a minor penalty for ignoring the second best class or even all best classes (in case of lexica). Note that this is a combinatorial score which does not reflect the original ConfidenceConfidenceConfidenceConfidenceConfidenceconfidence of the best ClassClassClassClassClassclassVal.

Parallelization

• 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_knndo_ocr_word_knnDoOcrWordKnndo_ocr_word_knnDoOcrWordKnnDoOcrWordKnn returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.

Possible Predecessors

trainf_ocr_class_knntrainf_ocr_class_knnTrainfOcrClassKnntrainf_ocr_class_knnTrainfOcrClassKnnTrainfOcrClassKnn, read_ocr_class_knnread_ocr_class_knnReadOcrClassKnnread_ocr_class_knnReadOcrClassKnnReadOcrClassKnn

Alternatives

do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnn

See also

create_ocr_class_knncreate_ocr_class_knnCreateOcrClassKnncreate_ocr_class_knnCreateOcrClassKnnCreateOcrClassKnn, classify_class_knnclassify_class_knnClassifyClassKnnclassify_class_knnClassifyClassKnnClassifyClassKnn

Module

OCR/OCV