Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009223712> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W3009223712 abstract "Handwritten numeral digit recognition is a classical problem in the field of computer vision, which has a wide range of applications in various fields including financial and post services. The accuracy of handwritten numeral digit recognition has been greatly improved by using deep learning in the past few years. However, deep learning relies on a large amount of training data and time-consuming calculation. In this paper, we adopt a transfer learning approach for handwritten numeral digit recognition and use both the multi-layer perceptron and convolutional neural network models to share the feature extraction process among five handwritten numerical datasets, namely, Tibetan, Arabic, Bangla, Devanagari, and Telugu. We compare the transfer learning scheme with the model based on a single dataset. We find that using the transfer learning method can significantly reduce the training time of the deep learning models, and slightly reduces the recognition accuracy." @default.
- W3009223712 created "2020-03-13" @default.
- W3009223712 creator A5021019207 @default.
- W3009223712 date "2020-01-12" @default.
- W3009223712 modified "2023-09-23" @default.
- W3009223712 title "A Transfer Learning Approach for Handwritten Numeral Digit Recognition" @default.
- W3009223712 cites W2112796928 @default.
- W3009223712 cites W2138270545 @default.
- W3009223712 cites W2338128728 @default.
- W3009223712 cites W2899619587 @default.
- W3009223712 cites W2919115771 @default.
- W3009223712 doi "https://doi.org/10.1145/3378936.3378970" @default.
- W3009223712 hasPublicationYear "2020" @default.
- W3009223712 type Work @default.
- W3009223712 sameAs 3009223712 @default.
- W3009223712 citedByCount "5" @default.
- W3009223712 countsByYear W30092237122021 @default.
- W3009223712 countsByYear W30092237122022 @default.
- W3009223712 crossrefType "proceedings-article" @default.
- W3009223712 hasAuthorship W3009223712A5021019207 @default.
- W3009223712 hasConcept C150899416 @default.
- W3009223712 hasConcept C154945302 @default.
- W3009223712 hasConcept C173608175 @default.
- W3009223712 hasConcept C204160518 @default.
- W3009223712 hasConcept C204321447 @default.
- W3009223712 hasConcept C2776175482 @default.
- W3009223712 hasConcept C28490314 @default.
- W3009223712 hasConcept C2984784707 @default.
- W3009223712 hasConcept C33923547 @default.
- W3009223712 hasConcept C41008148 @default.
- W3009223712 hasConcept C50644808 @default.
- W3009223712 hasConcept C94375191 @default.
- W3009223712 hasConcept C94957134 @default.
- W3009223712 hasConceptScore W3009223712C150899416 @default.
- W3009223712 hasConceptScore W3009223712C154945302 @default.
- W3009223712 hasConceptScore W3009223712C173608175 @default.
- W3009223712 hasConceptScore W3009223712C204160518 @default.
- W3009223712 hasConceptScore W3009223712C204321447 @default.
- W3009223712 hasConceptScore W3009223712C2776175482 @default.
- W3009223712 hasConceptScore W3009223712C28490314 @default.
- W3009223712 hasConceptScore W3009223712C2984784707 @default.
- W3009223712 hasConceptScore W3009223712C33923547 @default.
- W3009223712 hasConceptScore W3009223712C41008148 @default.
- W3009223712 hasConceptScore W3009223712C50644808 @default.
- W3009223712 hasConceptScore W3009223712C94375191 @default.
- W3009223712 hasConceptScore W3009223712C94957134 @default.
- W3009223712 hasLocation W30092237121 @default.
- W3009223712 hasOpenAccess W3009223712 @default.
- W3009223712 hasPrimaryLocation W30092237121 @default.
- W3009223712 hasRelatedWork W1030110109 @default.
- W3009223712 hasRelatedWork W1494440056 @default.
- W3009223712 hasRelatedWork W1891915803 @default.
- W3009223712 hasRelatedWork W192288062 @default.
- W3009223712 hasRelatedWork W2140531366 @default.
- W3009223712 hasRelatedWork W2188882424 @default.
- W3009223712 hasRelatedWork W2373103847 @default.
- W3009223712 hasRelatedWork W2911525106 @default.
- W3009223712 hasRelatedWork W2955174294 @default.
- W3009223712 hasRelatedWork W3009223712 @default.
- W3009223712 isParatext "false" @default.
- W3009223712 isRetracted "false" @default.
- W3009223712 magId "3009223712" @default.
- W3009223712 workType "article" @default.