Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310621664> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4310621664 abstract "Because of the natural conditions of license plate images, the Optical Character Recognition (OCR) of these images is generally a challenging problem. OCR systems are utilized in edge devices with limited computation power. Despite the considerable progress of deep neural networks, state-of-the-art models are not always an excellent solution to this problem. Most models have many parameters, and in practice, they need many resources to train, maintain and implement on edge devices. We propose a lightweight model based on Visual Transformer architecture and achieve competitive results against traditional CRNN models. Due to the lack of a rich and large-scale dataset for Persian license plates, we gathered and annotated 1.3M images of license plates in various natural conditions from different points of view and different cameras. We call this dataset as LicenseNet. Our proposed model achieves 77.25% accuracy against CNN models with 75.18% accuracy and embedded OCR models in cameras with 60.37% accuracy on the LicenseNet test set. Furthermore, we achieved better accuracy with 3.21 times fewer training parameters than previously proposed models." @default.
- W4310621664 created "2022-12-13" @default.
- W4310621664 creator A5017944744 @default.
- W4310621664 creator A5020868230 @default.
- W4310621664 creator A5047019835 @default.
- W4310621664 date "2022-11-17" @default.
- W4310621664 modified "2023-10-05" @default.
- W4310621664 title "MultiPath ViT OCR: A Lightweight Visual Transformer-based License Plate Optical Character Recognition" @default.
- W4310621664 cites W2069143585 @default.
- W4310621664 cites W2108598243 @default.
- W4310621664 cites W2140511609 @default.
- W4310621664 cites W2194187530 @default.
- W4310621664 cites W3119163485 @default.
- W4310621664 cites W3138516171 @default.
- W4310621664 doi "https://doi.org/10.1109/iccke57176.2022.9960026" @default.
- W4310621664 hasPublicationYear "2022" @default.
- W4310621664 type Work @default.
- W4310621664 citedByCount "1" @default.
- W4310621664 countsByYear W43106216642023 @default.
- W4310621664 crossrefType "proceedings-article" @default.
- W4310621664 hasAuthorship W4310621664A5017944744 @default.
- W4310621664 hasAuthorship W4310621664A5020868230 @default.
- W4310621664 hasAuthorship W4310621664A5047019835 @default.
- W4310621664 hasConcept C111919701 @default.
- W4310621664 hasConcept C11413529 @default.
- W4310621664 hasConcept C115961682 @default.
- W4310621664 hasConcept C119599485 @default.
- W4310621664 hasConcept C127413603 @default.
- W4310621664 hasConcept C138236772 @default.
- W4310621664 hasConcept C153180895 @default.
- W4310621664 hasConcept C154945302 @default.
- W4310621664 hasConcept C165801399 @default.
- W4310621664 hasConcept C2780560020 @default.
- W4310621664 hasConcept C28490314 @default.
- W4310621664 hasConcept C2987247673 @default.
- W4310621664 hasConcept C31972630 @default.
- W4310621664 hasConcept C41008148 @default.
- W4310621664 hasConcept C45374587 @default.
- W4310621664 hasConcept C546480517 @default.
- W4310621664 hasConcept C66322947 @default.
- W4310621664 hasConcept C79974875 @default.
- W4310621664 hasConceptScore W4310621664C111919701 @default.
- W4310621664 hasConceptScore W4310621664C11413529 @default.
- W4310621664 hasConceptScore W4310621664C115961682 @default.
- W4310621664 hasConceptScore W4310621664C119599485 @default.
- W4310621664 hasConceptScore W4310621664C127413603 @default.
- W4310621664 hasConceptScore W4310621664C138236772 @default.
- W4310621664 hasConceptScore W4310621664C153180895 @default.
- W4310621664 hasConceptScore W4310621664C154945302 @default.
- W4310621664 hasConceptScore W4310621664C165801399 @default.
- W4310621664 hasConceptScore W4310621664C2780560020 @default.
- W4310621664 hasConceptScore W4310621664C28490314 @default.
- W4310621664 hasConceptScore W4310621664C2987247673 @default.
- W4310621664 hasConceptScore W4310621664C31972630 @default.
- W4310621664 hasConceptScore W4310621664C41008148 @default.
- W4310621664 hasConceptScore W4310621664C45374587 @default.
- W4310621664 hasConceptScore W4310621664C546480517 @default.
- W4310621664 hasConceptScore W4310621664C66322947 @default.
- W4310621664 hasConceptScore W4310621664C79974875 @default.
- W4310621664 hasLocation W43106216641 @default.
- W4310621664 hasOpenAccess W4310621664 @default.
- W4310621664 hasPrimaryLocation W43106216641 @default.
- W4310621664 hasRelatedWork W1998599144 @default.
- W4310621664 hasRelatedWork W2052601356 @default.
- W4310621664 hasRelatedWork W2167335035 @default.
- W4310621664 hasRelatedWork W2546390685 @default.
- W4310621664 hasRelatedWork W2596612428 @default.
- W4310621664 hasRelatedWork W2991232105 @default.
- W4310621664 hasRelatedWork W3142277649 @default.
- W4310621664 hasRelatedWork W3185370371 @default.
- W4310621664 hasRelatedWork W3216111238 @default.
- W4310621664 hasRelatedWork W4287068517 @default.
- W4310621664 isParatext "false" @default.
- W4310621664 isRetracted "false" @default.
- W4310621664 workType "article" @default.