Matches in SemOpenAlex for { <https://semopenalex.org/work/W2004663190> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2004663190 endingPage "493" @default.
- W2004663190 startingPage "484" @default.
- W2004663190 abstract "This paper proposes an approach based on the statistical modeling and learning of neighboring characters to extract multilingual texts in images. The case of three neighboring characters is represented as the Gaussian mixture model and discriminated from other cases by the corresponding 'pseudo-probability' defined under Bayes framework. Based on this modeling, text extraction is completed through labeling each connected component in the binary image as character or non-character according to its neighbors, where a mathematical morphology based method is introduced to detect and connect the separated parts of each character, and a Voronoi partition based method is advised to establish the neighborhoods of connected components. We further present a discriminative training algorithm based on the maximum-minimum similarity (MMS) criterion to estimate the parameters in the proposed text extraction approach. Experimental results in Chinese and English text extraction demonstrate the effectiveness of our approach trained with the MMS algorithm, which achieved the precision rate of 93.56% and the recall rate of 98.55% for the test data set. In the experiments, we also show that the MMS provides significant improvement of overall performance, compared with influential training criterions of the maximum likelihood (ML) and the maximum classification error (MCE)." @default.
- W2004663190 created "2016-06-24" @default.
- W2004663190 creator A5061964691 @default.
- W2004663190 creator A5064291165 @default.
- W2004663190 creator A5085061478 @default.
- W2004663190 date "2008-02-01" @default.
- W2004663190 modified "2023-10-18" @default.
- W2004663190 title "Gaussian mixture modeling and learning of neighboring characters for multilingual text extraction in images" @default.
- W2004663190 cites W1969811075 @default.
- W2004663190 cites W1972774730 @default.
- W2004663190 cites W1986926502 @default.
- W2004663190 cites W2025638429 @default.
- W2004663190 cites W2027883219 @default.
- W2004663190 cites W2121839820 @default.
- W2004663190 cites W2135407189 @default.
- W2004663190 cites W2145268945 @default.
- W2004663190 cites W2158289097 @default.
- W2004663190 cites W2167014701 @default.
- W2004663190 doi "https://doi.org/10.1016/j.patcog.2007.06.004" @default.
- W2004663190 hasPublicationYear "2008" @default.
- W2004663190 type Work @default.
- W2004663190 sameAs 2004663190 @default.
- W2004663190 citedByCount "43" @default.
- W2004663190 countsByYear W20046631902012 @default.
- W2004663190 countsByYear W20046631902013 @default.
- W2004663190 countsByYear W20046631902014 @default.
- W2004663190 countsByYear W20046631902015 @default.
- W2004663190 countsByYear W20046631902016 @default.
- W2004663190 countsByYear W20046631902017 @default.
- W2004663190 countsByYear W20046631902018 @default.
- W2004663190 countsByYear W20046631902019 @default.
- W2004663190 countsByYear W20046631902020 @default.
- W2004663190 countsByYear W20046631902021 @default.
- W2004663190 countsByYear W20046631902022 @default.
- W2004663190 countsByYear W20046631902023 @default.
- W2004663190 crossrefType "journal-article" @default.
- W2004663190 hasAuthorship W2004663190A5061964691 @default.
- W2004663190 hasAuthorship W2004663190A5064291165 @default.
- W2004663190 hasAuthorship W2004663190A5085061478 @default.
- W2004663190 hasConcept C121332964 @default.
- W2004663190 hasConcept C153180895 @default.
- W2004663190 hasConcept C154945302 @default.
- W2004663190 hasConcept C163716315 @default.
- W2004663190 hasConcept C185592680 @default.
- W2004663190 hasConcept C204321447 @default.
- W2004663190 hasConcept C41008148 @default.
- W2004663190 hasConcept C43617362 @default.
- W2004663190 hasConcept C4725764 @default.
- W2004663190 hasConcept C61224824 @default.
- W2004663190 hasConcept C62520636 @default.
- W2004663190 hasConceptScore W2004663190C121332964 @default.
- W2004663190 hasConceptScore W2004663190C153180895 @default.
- W2004663190 hasConceptScore W2004663190C154945302 @default.
- W2004663190 hasConceptScore W2004663190C163716315 @default.
- W2004663190 hasConceptScore W2004663190C185592680 @default.
- W2004663190 hasConceptScore W2004663190C204321447 @default.
- W2004663190 hasConceptScore W2004663190C41008148 @default.
- W2004663190 hasConceptScore W2004663190C43617362 @default.
- W2004663190 hasConceptScore W2004663190C4725764 @default.
- W2004663190 hasConceptScore W2004663190C61224824 @default.
- W2004663190 hasConceptScore W2004663190C62520636 @default.
- W2004663190 hasIssue "2" @default.
- W2004663190 hasLocation W20046631901 @default.
- W2004663190 hasOpenAccess W2004663190 @default.
- W2004663190 hasPrimaryLocation W20046631901 @default.
- W2004663190 hasRelatedWork W1562793155 @default.
- W2004663190 hasRelatedWork W2003627431 @default.
- W2004663190 hasRelatedWork W2033914206 @default.
- W2004663190 hasRelatedWork W2076520961 @default.
- W2004663190 hasRelatedWork W2107898784 @default.
- W2004663190 hasRelatedWork W2293457016 @default.
- W2004663190 hasRelatedWork W2433217581 @default.
- W2004663190 hasRelatedWork W2789919619 @default.
- W2004663190 hasRelatedWork W2954309397 @default.
- W2004663190 hasRelatedWork W3169305685 @default.
- W2004663190 hasVolume "41" @default.
- W2004663190 isParatext "false" @default.
- W2004663190 isRetracted "false" @default.
- W2004663190 magId "2004663190" @default.
- W2004663190 workType "article" @default.