Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048313648> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3048313648 endingPage "107577" @default.
- W3048313648 startingPage "107577" @default.
- W3048313648 abstract "Artificial neural networks have been shown significant performance in various image-to-image conversion tasks. However, complex conversions often require a large number of images for model training. Therefore, we propose a convolutional model for image-to-image conversions using a pipeline of simpler image processing modules. To verify our proposed approach, we use a document image binarization as the task. Document image binarization is an important process that affects the accuracy of document analysis and recognition. In this paper, we propose a novel document binarization method called Cascading Modular U-Nets (CMU-Nets). CMU-Nets consist of pre-trained modular modules useful for overcoming the problem of a shortage of training images. We also propose a novel cascading scheme for improving overall cascading model performance. We verify the proposed model on all available Document Image Binarization Competition (DIBCO) and the Handwritten-DIBCO (H-DIBCO) datasets." @default.
- W3048313648 created "2020-08-13" @default.
- W3048313648 creator A5048120409 @default.
- W3048313648 creator A5051387162 @default.
- W3048313648 creator A5081518382 @default.
- W3048313648 date "2021-01-01" @default.
- W3048313648 modified "2023-10-17" @default.
- W3048313648 title "Complex image processing with less data—Document image binarization by integrating multiple pre-trained U-Net modules" @default.
- W3048313648 cites W1983039069 @default.
- W3048313648 cites W2058471322 @default.
- W3048313648 cites W2091863778 @default.
- W3048313648 cites W2096832794 @default.
- W3048313648 cites W2103233308 @default.
- W3048313648 cites W2112215040 @default.
- W3048313648 cites W2112796928 @default.
- W3048313648 cites W2128060444 @default.
- W3048313648 cites W2133059825 @default.
- W3048313648 cites W2154741421 @default.
- W3048313648 cites W2156605212 @default.
- W3048313648 cites W2168445392 @default.
- W3048313648 cites W2395709053 @default.
- W3048313648 cites W2751352153 @default.
- W3048313648 cites W2759766068 @default.
- W3048313648 cites W2911064732 @default.
- W3048313648 cites W2912989244 @default.
- W3048313648 cites W2957223244 @default.
- W3048313648 cites W2963881378 @default.
- W3048313648 cites W2988314300 @default.
- W3048313648 doi "https://doi.org/10.1016/j.patcog.2020.107577" @default.
- W3048313648 hasPublicationYear "2021" @default.
- W3048313648 type Work @default.
- W3048313648 sameAs 3048313648 @default.
- W3048313648 citedByCount "36" @default.
- W3048313648 countsByYear W30483136482021 @default.
- W3048313648 countsByYear W30483136482022 @default.
- W3048313648 countsByYear W30483136482023 @default.
- W3048313648 crossrefType "journal-article" @default.
- W3048313648 hasAuthorship W3048313648A5048120409 @default.
- W3048313648 hasAuthorship W3048313648A5051387162 @default.
- W3048313648 hasAuthorship W3048313648A5081518382 @default.
- W3048313648 hasConcept C101468663 @default.
- W3048313648 hasConcept C111919701 @default.
- W3048313648 hasConcept C115961682 @default.
- W3048313648 hasConcept C138885662 @default.
- W3048313648 hasConcept C153180895 @default.
- W3048313648 hasConcept C154945302 @default.
- W3048313648 hasConcept C194051981 @default.
- W3048313648 hasConcept C199360897 @default.
- W3048313648 hasConcept C2778137410 @default.
- W3048313648 hasConcept C31972630 @default.
- W3048313648 hasConcept C41008148 @default.
- W3048313648 hasConcept C41895202 @default.
- W3048313648 hasConcept C43521106 @default.
- W3048313648 hasConcept C81363708 @default.
- W3048313648 hasConcept C9417928 @default.
- W3048313648 hasConcept C98045186 @default.
- W3048313648 hasConceptScore W3048313648C101468663 @default.
- W3048313648 hasConceptScore W3048313648C111919701 @default.
- W3048313648 hasConceptScore W3048313648C115961682 @default.
- W3048313648 hasConceptScore W3048313648C138885662 @default.
- W3048313648 hasConceptScore W3048313648C153180895 @default.
- W3048313648 hasConceptScore W3048313648C154945302 @default.
- W3048313648 hasConceptScore W3048313648C194051981 @default.
- W3048313648 hasConceptScore W3048313648C199360897 @default.
- W3048313648 hasConceptScore W3048313648C2778137410 @default.
- W3048313648 hasConceptScore W3048313648C31972630 @default.
- W3048313648 hasConceptScore W3048313648C41008148 @default.
- W3048313648 hasConceptScore W3048313648C41895202 @default.
- W3048313648 hasConceptScore W3048313648C43521106 @default.
- W3048313648 hasConceptScore W3048313648C81363708 @default.
- W3048313648 hasConceptScore W3048313648C9417928 @default.
- W3048313648 hasConceptScore W3048313648C98045186 @default.
- W3048313648 hasLocation W30483136481 @default.
- W3048313648 hasOpenAccess W3048313648 @default.
- W3048313648 hasPrimaryLocation W30483136481 @default.
- W3048313648 hasRelatedWork W2175746458 @default.
- W3048313648 hasRelatedWork W2613736958 @default.
- W3048313648 hasRelatedWork W2732542196 @default.
- W3048313648 hasRelatedWork W2738221750 @default.
- W3048313648 hasRelatedWork W2760085659 @default.
- W3048313648 hasRelatedWork W2883200793 @default.
- W3048313648 hasRelatedWork W2899307613 @default.
- W3048313648 hasRelatedWork W3012978760 @default.
- W3048313648 hasRelatedWork W3093612317 @default.
- W3048313648 hasRelatedWork W4239686595 @default.
- W3048313648 hasVolume "109" @default.
- W3048313648 isParatext "false" @default.
- W3048313648 isRetracted "false" @default.
- W3048313648 magId "3048313648" @default.
- W3048313648 workType "article" @default.