Matches in SemOpenAlex for { <https://semopenalex.org/work/W3082022228> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3082022228 endingPage "107621" @default.
- W3082022228 startingPage "107621" @default.
- W3082022228 abstract "Abstract Dewarping is a necessary preprocessing step to recognize text from a distorted camera captured document image. According to recent literature, deep learning-based approaches perform with higher accuracy in similar domains. The deep learning-based neural networks are not yet fully explored in the domain of dewarping. To fill this gap, we propose a dewarping approach based on the convolutional neural network. A large number of images are required to train such networks. However, it is a tedious job to capture such a large number of images. Hence, it is required to generate synthetic warped images for the training phase of the deep learning-based neural network. The existing synthetic warped image generation methods are heuristic-based. In this paper, we propose a novel mathematical model for the generation of warped images. The proposed model takes some parameters such as depth of the surface, camera angle, and camera position and generates the corresponding warped image. These parameters are the ground truth for that particular warped image. We use a Convolutional Neural Network (CNN) based model to estimate the warping parameters from a 2D warped image for dewarping. In the training phase of CNN based model, the synthetic images and their corresponding ground truth are used. Next, the trained model is used to dewarp the unknown warped images. The performance of the proposed warping model is analyzed. Finally, the proposed dewarping method is compared with existing approaches. In both cases, the results are encouraging." @default.
- W3082022228 created "2020-09-08" @default.
- W3082022228 creator A5006106217 @default.
- W3082022228 creator A5025905668 @default.
- W3082022228 creator A5047820605 @default.
- W3082022228 date "2021-01-01" @default.
- W3082022228 modified "2023-09-23" @default.
- W3082022228 title "A theoretical justification of warping generation for dewarping using CNN" @default.
- W3082022228 cites W1967391099 @default.
- W3082022228 cites W2031746509 @default.
- W3082022228 cites W2038037829 @default.
- W3082022228 cites W2091722741 @default.
- W3082022228 cites W2120449447 @default.
- W3082022228 cites W2133665775 @default.
- W3082022228 cites W2149884040 @default.
- W3082022228 cites W2159374825 @default.
- W3082022228 cites W2170332640 @default.
- W3082022228 cites W236100371 @default.
- W3082022228 cites W2791307013 @default.
- W3082022228 cites W2934832377 @default.
- W3082022228 cites W2997072009 @default.
- W3082022228 cites W3033130864 @default.
- W3082022228 cites W3033841690 @default.
- W3082022228 cites W3036768193 @default.
- W3082022228 cites W3038203375 @default.
- W3082022228 cites W3047176958 @default.
- W3082022228 cites W2600160525 @default.
- W3082022228 doi "https://doi.org/10.1016/j.patcog.2020.107621" @default.
- W3082022228 hasPublicationYear "2021" @default.
- W3082022228 type Work @default.
- W3082022228 sameAs 3082022228 @default.
- W3082022228 citedByCount "5" @default.
- W3082022228 countsByYear W30820222282021 @default.
- W3082022228 countsByYear W30820222282022 @default.
- W3082022228 countsByYear W30820222282023 @default.
- W3082022228 crossrefType "journal-article" @default.
- W3082022228 hasAuthorship W3082022228A5006106217 @default.
- W3082022228 hasAuthorship W3082022228A5025905668 @default.
- W3082022228 hasAuthorship W3082022228A5047820605 @default.
- W3082022228 hasConcept C153180895 @default.
- W3082022228 hasConcept C154945302 @default.
- W3082022228 hasConcept C157202957 @default.
- W3082022228 hasConcept C204321447 @default.
- W3082022228 hasConcept C28490314 @default.
- W3082022228 hasConcept C31972630 @default.
- W3082022228 hasConcept C33923547 @default.
- W3082022228 hasConcept C41008148 @default.
- W3082022228 hasConceptScore W3082022228C153180895 @default.
- W3082022228 hasConceptScore W3082022228C154945302 @default.
- W3082022228 hasConceptScore W3082022228C157202957 @default.
- W3082022228 hasConceptScore W3082022228C204321447 @default.
- W3082022228 hasConceptScore W3082022228C28490314 @default.
- W3082022228 hasConceptScore W3082022228C31972630 @default.
- W3082022228 hasConceptScore W3082022228C33923547 @default.
- W3082022228 hasConceptScore W3082022228C41008148 @default.
- W3082022228 hasLocation W30820222281 @default.
- W3082022228 hasOpenAccess W3082022228 @default.
- W3082022228 hasPrimaryLocation W30820222281 @default.
- W3082022228 hasRelatedWork W2059729733 @default.
- W3082022228 hasRelatedWork W2116300362 @default.
- W3082022228 hasRelatedWork W2127108814 @default.
- W3082022228 hasRelatedWork W2143630701 @default.
- W3082022228 hasRelatedWork W2370766994 @default.
- W3082022228 hasRelatedWork W2621079708 @default.
- W3082022228 hasRelatedWork W2779438614 @default.
- W3082022228 hasRelatedWork W3041198820 @default.
- W3082022228 hasRelatedWork W3190512878 @default.
- W3082022228 hasRelatedWork W1487047144 @default.
- W3082022228 hasVolume "109" @default.
- W3082022228 isParatext "false" @default.
- W3082022228 isRetracted "false" @default.
- W3082022228 magId "3082022228" @default.
- W3082022228 workType "article" @default.