Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366338872> ?p ?o ?g. }
- W4366338872 endingPage "15773" @default.
- W4366338872 startingPage "15759" @default.
- W4366338872 abstract "Abstract Handwritten text recognition, i.e., the conversion of scanned handwritten documents into machine-readable text, is a complex exercise due to the variability and complexity of handwriting. A common approach in handwritten text recognition consists of a feature extraction step followed by a recognizer. In this paper, we propose a novel DNN architecture for handwritten text recognition that extracts discrete representation from the input text-line image. The proposed model is constructed of an encoder–decoder network with an added quantization layer which applies a dictionary of representative vectors to discretize the latent variables. The dictionary and the network parameters are trained jointly through the k -means algorithm and back propagation, respectively. The performance of the suggested model is evaluated through conducting extensive experiments on five datasets, analyzing the effect of discrete representation on handwriting recognition. The results demonstrate that the use of feature discretization improves the performance of deep handwriting text recognition models when compared to the conventional DNN models with continuous representation. Specifically, the character error rate is decreased by $$22%$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mn>22</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> and $$21.1%$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mn>21.1</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> on IAM and ICFHR18 datasets, respectively." @default.
- W4366338872 created "2023-04-20" @default.
- W4366338872 creator A5013655243 @default.
- W4366338872 creator A5025092398 @default.
- W4366338872 date "2023-04-18" @default.
- W4366338872 modified "2023-09-26" @default.
- W4366338872 title "Discrete representation learning for handwritten text recognition" @default.
- W4366338872 cites W1436594442 @default.
- W4366338872 cites W1441847231 @default.
- W4366338872 cites W1662005137 @default.
- W4366338872 cites W1993155451 @default.
- W4366338872 cites W2049105599 @default.
- W4366338872 cites W2085229926 @default.
- W4366338872 cites W2100495367 @default.
- W4366338872 cites W2111464917 @default.
- W4366338872 cites W2127141656 @default.
- W4366338872 cites W2131831414 @default.
- W4366338872 cites W2133552271 @default.
- W4366338872 cites W2152928267 @default.
- W4366338872 cites W2155793192 @default.
- W4366338872 cites W2162395775 @default.
- W4366338872 cites W2194187530 @default.
- W4366338872 cites W2342468814 @default.
- W4366338872 cites W2345904788 @default.
- W4366338872 cites W2573601984 @default.
- W4366338872 cites W2761448188 @default.
- W4366338872 cites W2785875661 @default.
- W4366338872 cites W2786429113 @default.
- W4366338872 cites W2786974559 @default.
- W4366338872 cites W2793404167 @default.
- W4366338872 cites W2895359355 @default.
- W4366338872 cites W2904714269 @default.
- W4366338872 cites W2906299545 @default.
- W4366338872 cites W2946921758 @default.
- W4366338872 cites W2959965583 @default.
- W4366338872 cites W2962707697 @default.
- W4366338872 cites W2963775347 @default.
- W4366338872 cites W2964325005 @default.
- W4366338872 cites W2965066169 @default.
- W4366338872 cites W2998382406 @default.
- W4366338872 cites W3034726763 @default.
- W4366338872 cites W3038203375 @default.
- W4366338872 cites W3043224321 @default.
- W4366338872 cites W3101358972 @default.
- W4366338872 cites W3102713119 @default.
- W4366338872 cites W3110775055 @default.
- W4366338872 cites W3112447751 @default.
- W4366338872 cites W3160407927 @default.
- W4366338872 cites W3163192001 @default.
- W4366338872 cites W3174205643 @default.
- W4366338872 cites W3195409404 @default.
- W4366338872 doi "https://doi.org/10.1007/s00521-023-08445-9" @default.
- W4366338872 hasPublicationYear "2023" @default.
- W4366338872 type Work @default.
- W4366338872 citedByCount "0" @default.
- W4366338872 crossrefType "journal-article" @default.
- W4366338872 hasAuthorship W4366338872A5013655243 @default.
- W4366338872 hasAuthorship W4366338872A5025092398 @default.
- W4366338872 hasBestOaLocation W43663388721 @default.
- W4366338872 hasConcept C112640561 @default.
- W4366338872 hasConcept C11413529 @default.
- W4366338872 hasConcept C134306372 @default.
- W4366338872 hasConcept C153180895 @default.
- W4366338872 hasConcept C154945302 @default.
- W4366338872 hasConcept C17744445 @default.
- W4366338872 hasConcept C199539241 @default.
- W4366338872 hasConcept C2776359362 @default.
- W4366338872 hasConcept C2779386606 @default.
- W4366338872 hasConcept C28490314 @default.
- W4366338872 hasConcept C33923547 @default.
- W4366338872 hasConcept C41008148 @default.
- W4366338872 hasConcept C50644808 @default.
- W4366338872 hasConcept C52622490 @default.
- W4366338872 hasConcept C73000952 @default.
- W4366338872 hasConcept C94625758 @default.
- W4366338872 hasConceptScore W4366338872C112640561 @default.
- W4366338872 hasConceptScore W4366338872C11413529 @default.
- W4366338872 hasConceptScore W4366338872C134306372 @default.
- W4366338872 hasConceptScore W4366338872C153180895 @default.
- W4366338872 hasConceptScore W4366338872C154945302 @default.
- W4366338872 hasConceptScore W4366338872C17744445 @default.
- W4366338872 hasConceptScore W4366338872C199539241 @default.
- W4366338872 hasConceptScore W4366338872C2776359362 @default.
- W4366338872 hasConceptScore W4366338872C2779386606 @default.
- W4366338872 hasConceptScore W4366338872C28490314 @default.
- W4366338872 hasConceptScore W4366338872C33923547 @default.
- W4366338872 hasConceptScore W4366338872C41008148 @default.
- W4366338872 hasConceptScore W4366338872C50644808 @default.
- W4366338872 hasConceptScore W4366338872C52622490 @default.
- W4366338872 hasConceptScore W4366338872C73000952 @default.
- W4366338872 hasConceptScore W4366338872C94625758 @default.
- W4366338872 hasFunder F4320325847 @default.
- W4366338872 hasIssue "21" @default.
- W4366338872 hasLocation W43663388721 @default.
- W4366338872 hasOpenAccess W4366338872 @default.
- W4366338872 hasPrimaryLocation W43663388721 @default.
- W4366338872 hasRelatedWork W1964120219 @default.
- W4366338872 hasRelatedWork W2136489243 @default.