Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912832679> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2912832679 abstract "In this paper, we present an end-to-end deep learning system for Chinese character recognition. We applied the system to recognize ID card photographed by smart phone in natural environment. The quality of ID card images was affected by illumination and shadow. We developed a preprocessing procedure to enhance the images and then to detect and extract Chinese characters and numbers from the images. The end-to-end deep convolutional neural network (CNN)consists of deep separable convolutional (DSC)layers, batch normalization (BN)layers, ReLu activation layers and residual connections to mitigate over-fitting and gradient vanish. To train the network, we constructed a dataset containing the 3765 most frequent Chinese characters. We tested the proposed system on a self-constructed Chinese character dataset and achieved an accuracy of 92.73%." @default.
- W2912832679 created "2019-02-21" @default.
- W2912832679 creator A5016478003 @default.
- W2912832679 creator A5030889163 @default.
- W2912832679 creator A5037995046 @default.
- W2912832679 creator A5039612950 @default.
- W2912832679 creator A5047581509 @default.
- W2912832679 creator A5062841020 @default.
- W2912832679 creator A5083627327 @default.
- W2912832679 date "2018-12-01" @default.
- W2912832679 modified "2023-09-27" @default.
- W2912832679 title "Chinese Character Recognition Based on Residual Separable Convolutional Neural Network" @default.
- W2912832679 cites W2032254851 @default.
- W2912832679 cites W2112796928 @default.
- W2912832679 cites W2242910226 @default.
- W2912832679 cites W2789943307 @default.
- W2912832679 doi "https://doi.org/10.1109/iccwamtip.2018.8632573" @default.
- W2912832679 hasPublicationYear "2018" @default.
- W2912832679 type Work @default.
- W2912832679 sameAs 2912832679 @default.
- W2912832679 citedByCount "1" @default.
- W2912832679 countsByYear W29128326792022 @default.
- W2912832679 crossrefType "proceedings-article" @default.
- W2912832679 hasAuthorship W2912832679A5016478003 @default.
- W2912832679 hasAuthorship W2912832679A5030889163 @default.
- W2912832679 hasAuthorship W2912832679A5037995046 @default.
- W2912832679 hasAuthorship W2912832679A5039612950 @default.
- W2912832679 hasAuthorship W2912832679A5047581509 @default.
- W2912832679 hasAuthorship W2912832679A5062841020 @default.
- W2912832679 hasAuthorship W2912832679A5083627327 @default.
- W2912832679 hasConcept C108583219 @default.
- W2912832679 hasConcept C11413529 @default.
- W2912832679 hasConcept C115961682 @default.
- W2912832679 hasConcept C136886441 @default.
- W2912832679 hasConcept C144024400 @default.
- W2912832679 hasConcept C153180895 @default.
- W2912832679 hasConcept C154945302 @default.
- W2912832679 hasConcept C155512373 @default.
- W2912832679 hasConcept C19165224 @default.
- W2912832679 hasConcept C2524010 @default.
- W2912832679 hasConcept C2777737414 @default.
- W2912832679 hasConcept C2780861071 @default.
- W2912832679 hasConcept C2781051154 @default.
- W2912832679 hasConcept C28490314 @default.
- W2912832679 hasConcept C33923547 @default.
- W2912832679 hasConcept C34736171 @default.
- W2912832679 hasConcept C41008148 @default.
- W2912832679 hasConcept C52622490 @default.
- W2912832679 hasConcept C546480517 @default.
- W2912832679 hasConcept C81363708 @default.
- W2912832679 hasConceptScore W2912832679C108583219 @default.
- W2912832679 hasConceptScore W2912832679C11413529 @default.
- W2912832679 hasConceptScore W2912832679C115961682 @default.
- W2912832679 hasConceptScore W2912832679C136886441 @default.
- W2912832679 hasConceptScore W2912832679C144024400 @default.
- W2912832679 hasConceptScore W2912832679C153180895 @default.
- W2912832679 hasConceptScore W2912832679C154945302 @default.
- W2912832679 hasConceptScore W2912832679C155512373 @default.
- W2912832679 hasConceptScore W2912832679C19165224 @default.
- W2912832679 hasConceptScore W2912832679C2524010 @default.
- W2912832679 hasConceptScore W2912832679C2777737414 @default.
- W2912832679 hasConceptScore W2912832679C2780861071 @default.
- W2912832679 hasConceptScore W2912832679C2781051154 @default.
- W2912832679 hasConceptScore W2912832679C28490314 @default.
- W2912832679 hasConceptScore W2912832679C33923547 @default.
- W2912832679 hasConceptScore W2912832679C34736171 @default.
- W2912832679 hasConceptScore W2912832679C41008148 @default.
- W2912832679 hasConceptScore W2912832679C52622490 @default.
- W2912832679 hasConceptScore W2912832679C546480517 @default.
- W2912832679 hasConceptScore W2912832679C81363708 @default.
- W2912832679 hasLocation W29128326791 @default.
- W2912832679 hasOpenAccess W2912832679 @default.
- W2912832679 hasPrimaryLocation W29128326791 @default.
- W2912832679 hasRelatedWork W1993918770 @default.
- W2912832679 hasRelatedWork W2401678287 @default.
- W2912832679 hasRelatedWork W2732542196 @default.
- W2912832679 hasRelatedWork W2760944304 @default.
- W2912832679 hasRelatedWork W2773120646 @default.
- W2912832679 hasRelatedWork W2791238083 @default.
- W2912832679 hasRelatedWork W2912832679 @default.
- W2912832679 hasRelatedWork W2984759351 @default.
- W2912832679 hasRelatedWork W3195938642 @default.
- W2912832679 hasRelatedWork W4229456164 @default.
- W2912832679 isParatext "false" @default.
- W2912832679 isRetracted "false" @default.
- W2912832679 magId "2912832679" @default.
- W2912832679 workType "article" @default.