Matches in SemOpenAlex for { <https://semopenalex.org/work/W2038329042> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2038329042 abstract "Our previous work has shown that the error correction of optical character recognition (OCR) on degraded historical machine-printed documents is improved with the use of multiple information sources and multiple OCR hypotheses including from multiple document image binarizations. The contributions of this paper are in demonstrating how diversity among multiple binarizations makes those improvements to OCR accuracy possible. We demonstrate the degree and breadth to which the information required for correction is distributed across multiple binarizations of a given document image. Our analysis reveals that the sources of these corrections are not limited to any single binarization and that the full range of binarizations holds information needed to achieve the best result as measured by the word error rate (WER) of the final OCR decision. Even binarizations with high WERs contribute to improving the final OCR. For the corpus used in this research, fully 2.68% of all tokens are corrected using hypotheses not found in the OCR of the binarized image with the lowest WER. Further, we show that the higher the WER of the OCR overall, the more the corrections are distributed among all binarizations of the document image." @default.
- W2038329042 created "2016-06-24" @default.
- W2038329042 creator A5065220846 @default.
- W2038329042 creator A5077722320 @default.
- W2038329042 creator A5090791372 @default.
- W2038329042 date "2013-08-24" @default.
- W2038329042 modified "2023-09-27" @default.
- W2038329042 title "Why multiple document image binarizations improve OCR" @default.
- W2038329042 cites W1972016971 @default.
- W2038329042 cites W1975679321 @default.
- W2038329042 cites W2002638840 @default.
- W2038329042 cites W2013767392 @default.
- W2038329042 cites W2024348326 @default.
- W2038329042 cites W2045566081 @default.
- W2038329042 cites W2063828767 @default.
- W2038329042 cites W2069189382 @default.
- W2038329042 cites W2095581275 @default.
- W2038329042 cites W2104543051 @default.
- W2038329042 cites W2114781615 @default.
- W2038329042 cites W2118756867 @default.
- W2038329042 cites W2144872023 @default.
- W2038329042 cites W2158275940 @default.
- W2038329042 doi "https://doi.org/10.1145/2501115.2501126" @default.
- W2038329042 hasPublicationYear "2013" @default.
- W2038329042 type Work @default.
- W2038329042 sameAs 2038329042 @default.
- W2038329042 citedByCount "7" @default.
- W2038329042 countsByYear W20383290422013 @default.
- W2038329042 countsByYear W20383290422014 @default.
- W2038329042 countsByYear W20383290422017 @default.
- W2038329042 countsByYear W20383290422018 @default.
- W2038329042 countsByYear W20383290422019 @default.
- W2038329042 crossrefType "proceedings-article" @default.
- W2038329042 hasAuthorship W2038329042A5065220846 @default.
- W2038329042 hasAuthorship W2038329042A5077722320 @default.
- W2038329042 hasAuthorship W2038329042A5090791372 @default.
- W2038329042 hasConcept C103088060 @default.
- W2038329042 hasConcept C11413529 @default.
- W2038329042 hasConcept C115961682 @default.
- W2038329042 hasConcept C124504099 @default.
- W2038329042 hasConcept C153180895 @default.
- W2038329042 hasConcept C154945302 @default.
- W2038329042 hasConcept C159985019 @default.
- W2038329042 hasConcept C192562407 @default.
- W2038329042 hasConcept C204321447 @default.
- W2038329042 hasConcept C204323151 @default.
- W2038329042 hasConcept C23123220 @default.
- W2038329042 hasConcept C2524010 @default.
- W2038329042 hasConcept C2778371909 @default.
- W2038329042 hasConcept C2780861071 @default.
- W2038329042 hasConcept C2988504005 @default.
- W2038329042 hasConcept C33923547 @default.
- W2038329042 hasConcept C40969351 @default.
- W2038329042 hasConcept C41008148 @default.
- W2038329042 hasConcept C546480517 @default.
- W2038329042 hasConcept C90805587 @default.
- W2038329042 hasConceptScore W2038329042C103088060 @default.
- W2038329042 hasConceptScore W2038329042C11413529 @default.
- W2038329042 hasConceptScore W2038329042C115961682 @default.
- W2038329042 hasConceptScore W2038329042C124504099 @default.
- W2038329042 hasConceptScore W2038329042C153180895 @default.
- W2038329042 hasConceptScore W2038329042C154945302 @default.
- W2038329042 hasConceptScore W2038329042C159985019 @default.
- W2038329042 hasConceptScore W2038329042C192562407 @default.
- W2038329042 hasConceptScore W2038329042C204321447 @default.
- W2038329042 hasConceptScore W2038329042C204323151 @default.
- W2038329042 hasConceptScore W2038329042C23123220 @default.
- W2038329042 hasConceptScore W2038329042C2524010 @default.
- W2038329042 hasConceptScore W2038329042C2778371909 @default.
- W2038329042 hasConceptScore W2038329042C2780861071 @default.
- W2038329042 hasConceptScore W2038329042C2988504005 @default.
- W2038329042 hasConceptScore W2038329042C33923547 @default.
- W2038329042 hasConceptScore W2038329042C40969351 @default.
- W2038329042 hasConceptScore W2038329042C41008148 @default.
- W2038329042 hasConceptScore W2038329042C546480517 @default.
- W2038329042 hasConceptScore W2038329042C90805587 @default.
- W2038329042 hasLocation W20383290421 @default.
- W2038329042 hasOpenAccess W2038329042 @default.
- W2038329042 hasPrimaryLocation W20383290421 @default.
- W2038329042 hasRelatedWork W2104148441 @default.
- W2038329042 hasRelatedWork W2356293009 @default.
- W2038329042 hasRelatedWork W2363407155 @default.
- W2038329042 hasRelatedWork W2785385789 @default.
- W2038329042 hasRelatedWork W2804608824 @default.
- W2038329042 hasRelatedWork W3107474891 @default.
- W2038329042 hasRelatedWork W4292068860 @default.
- W2038329042 hasRelatedWork W71071520 @default.
- W2038329042 hasRelatedWork W77769009 @default.
- W2038329042 hasRelatedWork W3140870753 @default.
- W2038329042 isParatext "false" @default.
- W2038329042 isRetracted "false" @default.
- W2038329042 magId "2038329042" @default.
- W2038329042 workType "article" @default.