Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382280647> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4382280647 endingPage "2819" @default.
- W4382280647 startingPage "2819" @default.
- W4382280647 abstract "With the development of society, the intangible cultural heritage of Chinese Nüshu is in danger of extinction. To promote the research and popularization of traditional Chinese culture, we use deep learning to automatically detect and recognize handwritten Nüshu characters. To address difficulties such as the creation of a Nüshu character dataset, uneven samples, and difficulties in character recognition, we first build a large-scale handwritten Nüshu character dataset, HWNS2023, by using various data augmentation methods. This dataset contains 5500 Nüshu images and 1364 labeled character samples. Second, in this paper, we propose a two-stage scheme model combining GoogLeNet-tiny and YOLOv5-CBAM (SGooTY) for Nüshu recognition. In the first stage, five basic deep learning models including AlexNet, VGGNet16, GoogLeNet, MobileNetV3, and ResNet are trained and tested on the dataset, and the model structure is improved to enhance the accuracy of recognising handwritten Nüshu characters. In the second stage, we combine an object detection model to re-recognize misidentified handwritten Nüshu characters to ensure the accuracy of the overall system. Experimental results show that in the first stage, the improved model achieves the highest accuracy of 99.3% in recognising Nüshu characters, which significantly improves the recognition rate of handwritten Nüshu characters. After integrating the object recognition model, the overall recognition accuracy of the model reached 99.9%." @default.
- W4382280647 created "2023-06-28" @default.
- W4382280647 creator A5015944074 @default.
- W4382280647 creator A5052324354 @default.
- W4382280647 date "2023-06-26" @default.
- W4382280647 modified "2023-09-29" @default.
- W4382280647 title "SGooTY: A Scheme Combining the GoogLeNet-Tiny and YOLOv5-CBAM Models for Nüshu Recognition" @default.
- W4382280647 cites W1995875735 @default.
- W4382280647 cites W2097117768 @default.
- W4382280647 cites W2194775991 @default.
- W4382280647 cites W2418519490 @default.
- W4382280647 cites W2595505980 @default.
- W4382280647 cites W2787352719 @default.
- W4382280647 cites W2798258579 @default.
- W4382280647 cites W2884585870 @default.
- W4382280647 cites W2895359355 @default.
- W4382280647 cites W2900268290 @default.
- W4382280647 cites W2904970205 @default.
- W4382280647 cites W2915585559 @default.
- W4382280647 cites W2963037989 @default.
- W4382280647 cites W2974576579 @default.
- W4382280647 cites W3003222591 @default.
- W4382280647 cites W3004690717 @default.
- W4382280647 cites W3106228916 @default.
- W4382280647 cites W3153249728 @default.
- W4382280647 cites W3197424690 @default.
- W4382280647 cites W3202195514 @default.
- W4382280647 cites W3206824631 @default.
- W4382280647 cites W4212963611 @default.
- W4382280647 cites W4249306322 @default.
- W4382280647 cites W4296908399 @default.
- W4382280647 cites W4318465137 @default.
- W4382280647 cites W4323894636 @default.
- W4382280647 doi "https://doi.org/10.3390/electronics12132819" @default.
- W4382280647 hasPublicationYear "2023" @default.
- W4382280647 type Work @default.
- W4382280647 citedByCount "0" @default.
- W4382280647 crossrefType "journal-article" @default.
- W4382280647 hasAuthorship W4382280647A5015944074 @default.
- W4382280647 hasAuthorship W4382280647A5052324354 @default.
- W4382280647 hasBestOaLocation W43822806471 @default.
- W4382280647 hasConcept C108583219 @default.
- W4382280647 hasConcept C115961682 @default.
- W4382280647 hasConcept C134306372 @default.
- W4382280647 hasConcept C153180895 @default.
- W4382280647 hasConcept C154945302 @default.
- W4382280647 hasConcept C2524010 @default.
- W4382280647 hasConcept C2780861071 @default.
- W4382280647 hasConcept C2781051154 @default.
- W4382280647 hasConcept C28490314 @default.
- W4382280647 hasConcept C2987247673 @default.
- W4382280647 hasConcept C33923547 @default.
- W4382280647 hasConcept C41008148 @default.
- W4382280647 hasConcept C77618280 @default.
- W4382280647 hasConceptScore W4382280647C108583219 @default.
- W4382280647 hasConceptScore W4382280647C115961682 @default.
- W4382280647 hasConceptScore W4382280647C134306372 @default.
- W4382280647 hasConceptScore W4382280647C153180895 @default.
- W4382280647 hasConceptScore W4382280647C154945302 @default.
- W4382280647 hasConceptScore W4382280647C2524010 @default.
- W4382280647 hasConceptScore W4382280647C2780861071 @default.
- W4382280647 hasConceptScore W4382280647C2781051154 @default.
- W4382280647 hasConceptScore W4382280647C28490314 @default.
- W4382280647 hasConceptScore W4382280647C2987247673 @default.
- W4382280647 hasConceptScore W4382280647C33923547 @default.
- W4382280647 hasConceptScore W4382280647C41008148 @default.
- W4382280647 hasConceptScore W4382280647C77618280 @default.
- W4382280647 hasIssue "13" @default.
- W4382280647 hasLocation W43822806471 @default.
- W4382280647 hasOpenAccess W4382280647 @default.
- W4382280647 hasPrimaryLocation W43822806471 @default.
- W4382280647 hasRelatedWork W1969308216 @default.
- W4382280647 hasRelatedWork W2042046731 @default.
- W4382280647 hasRelatedWork W2118744957 @default.
- W4382280647 hasRelatedWork W2171915408 @default.
- W4382280647 hasRelatedWork W2361283250 @default.
- W4382280647 hasRelatedWork W2374412767 @default.
- W4382280647 hasRelatedWork W2380258347 @default.
- W4382280647 hasRelatedWork W2733060750 @default.
- W4382280647 hasRelatedWork W2766146978 @default.
- W4382280647 hasRelatedWork W2773120646 @default.
- W4382280647 hasVolume "12" @default.
- W4382280647 isParatext "false" @default.
- W4382280647 isRetracted "false" @default.
- W4382280647 workType "article" @default.