Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372350032> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4372350032 endingPage "5677" @default.
- W4372350032 startingPage "5677" @default.
- W4372350032 abstract "This paper aims to increase the accuracy of Kazakh handwriting text recognition (KHTR) using the generative adversarial network (GAN), where a handwriting word image generator and an image quality discriminator are constructed. In order to obtain a high-quality image of handwritten text, the multiple losses are intended to encourage the generator to learn the structural properties of the texts. In this case, the quality discriminator is trained on the basis of the relativistic loss function. Based on the proposed structure, the resulting document images not only preserve texture details but also generate different writer styles, which provides better OCR performance in public databases. With a self-created dataset, images of different types of handwriting styles were obtained, which will be used when training the network. The proposed approach allows for a character error rate (CER) of 11.15% and a word error rate (WER) of 25.65%." @default.
- W4372350032 created "2023-05-07" @default.
- W4372350032 creator A5037016760 @default.
- W4372350032 creator A5038486643 @default.
- W4372350032 creator A5058735039 @default.
- W4372350032 date "2023-05-05" @default.
- W4372350032 modified "2023-09-26" @default.
- W4372350032 title "Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models" @default.
- W4372350032 cites W2194187530 @default.
- W4372350032 cites W2603777577 @default.
- W4372350032 cites W2899945981 @default.
- W4372350032 cites W2954586346 @default.
- W4372350032 cites W2962770929 @default.
- W4372350032 cites W2982422766 @default.
- W4372350032 cites W3034904792 @default.
- W4372350032 cites W3118791215 @default.
- W4372350032 cites W3133428700 @default.
- W4372350032 cites W3160913560 @default.
- W4372350032 cites W3175789703 @default.
- W4372350032 cites W3176997265 @default.
- W4372350032 cites W4214752482 @default.
- W4372350032 cites W4224313859 @default.
- W4372350032 cites W4285712367 @default.
- W4372350032 cites W4293450989 @default.
- W4372350032 cites W4306835925 @default.
- W4372350032 cites W4319751163 @default.
- W4372350032 doi "https://doi.org/10.3390/app13095677" @default.
- W4372350032 hasPublicationYear "2023" @default.
- W4372350032 type Work @default.
- W4372350032 citedByCount "0" @default.
- W4372350032 crossrefType "journal-article" @default.
- W4372350032 hasAuthorship W4372350032A5037016760 @default.
- W4372350032 hasAuthorship W4372350032A5038486643 @default.
- W4372350032 hasAuthorship W4372350032A5058735039 @default.
- W4372350032 hasBestOaLocation W43723500321 @default.
- W4372350032 hasConcept C112640561 @default.
- W4372350032 hasConcept C115961682 @default.
- W4372350032 hasConcept C121332964 @default.
- W4372350032 hasConcept C153180895 @default.
- W4372350032 hasConcept C154945302 @default.
- W4372350032 hasConcept C163258240 @default.
- W4372350032 hasConcept C2524010 @default.
- W4372350032 hasConcept C2779386606 @default.
- W4372350032 hasConcept C2779803651 @default.
- W4372350032 hasConcept C2780861071 @default.
- W4372350032 hasConcept C2780992000 @default.
- W4372350032 hasConcept C28490314 @default.
- W4372350032 hasConcept C33923547 @default.
- W4372350032 hasConcept C39890363 @default.
- W4372350032 hasConcept C40969351 @default.
- W4372350032 hasConcept C41008148 @default.
- W4372350032 hasConcept C52622490 @default.
- W4372350032 hasConcept C62520636 @default.
- W4372350032 hasConcept C76155785 @default.
- W4372350032 hasConcept C90805587 @default.
- W4372350032 hasConcept C94915269 @default.
- W4372350032 hasConceptScore W4372350032C112640561 @default.
- W4372350032 hasConceptScore W4372350032C115961682 @default.
- W4372350032 hasConceptScore W4372350032C121332964 @default.
- W4372350032 hasConceptScore W4372350032C153180895 @default.
- W4372350032 hasConceptScore W4372350032C154945302 @default.
- W4372350032 hasConceptScore W4372350032C163258240 @default.
- W4372350032 hasConceptScore W4372350032C2524010 @default.
- W4372350032 hasConceptScore W4372350032C2779386606 @default.
- W4372350032 hasConceptScore W4372350032C2779803651 @default.
- W4372350032 hasConceptScore W4372350032C2780861071 @default.
- W4372350032 hasConceptScore W4372350032C2780992000 @default.
- W4372350032 hasConceptScore W4372350032C28490314 @default.
- W4372350032 hasConceptScore W4372350032C33923547 @default.
- W4372350032 hasConceptScore W4372350032C39890363 @default.
- W4372350032 hasConceptScore W4372350032C40969351 @default.
- W4372350032 hasConceptScore W4372350032C41008148 @default.
- W4372350032 hasConceptScore W4372350032C52622490 @default.
- W4372350032 hasConceptScore W4372350032C62520636 @default.
- W4372350032 hasConceptScore W4372350032C76155785 @default.
- W4372350032 hasConceptScore W4372350032C90805587 @default.
- W4372350032 hasConceptScore W4372350032C94915269 @default.
- W4372350032 hasIssue "9" @default.
- W4372350032 hasLocation W43723500321 @default.
- W4372350032 hasOpenAccess W4372350032 @default.
- W4372350032 hasPrimaryLocation W43723500321 @default.
- W4372350032 hasRelatedWork W2914998939 @default.
- W4372350032 hasRelatedWork W2923217310 @default.
- W4372350032 hasRelatedWork W3003183197 @default.
- W4372350032 hasRelatedWork W3082099965 @default.
- W4372350032 hasRelatedWork W3094325913 @default.
- W4372350032 hasRelatedWork W3097125773 @default.
- W4372350032 hasRelatedWork W3104956649 @default.
- W4372350032 hasRelatedWork W4200417262 @default.
- W4372350032 hasRelatedWork W4283584549 @default.
- W4372350032 hasRelatedWork W4288624664 @default.
- W4372350032 hasVolume "13" @default.
- W4372350032 isParatext "false" @default.
- W4372350032 isRetracted "false" @default.
- W4372350032 workType "article" @default.