Chronological attribution of Sinhalese inscriptions using deep learning approaches

IF 0.4 4区 综合性期刊 Q4 MULTIDISCIPLINARY SCIENCES
H.M.S.C.R. Heenkenda, T.G.I. Fernando
{"title":"Chronological attribution of Sinhalese inscriptions using deep learning approaches","authors":"H.M.S.C.R. Heenkenda, T.G.I. Fernando","doi":"10.4038/jnsfsr.v51i3.11200","DOIUrl":null,"url":null,"abstract":"A study of this caliber can be identified as a profound source for a wealth of knowledge as the aim of this study is to present chronological attribution of Sinhalese inscriptions based on deep learning approaches. Inscriptions shed light on a multitude of information such as chronicled civilizational thought, economic status, language evolution, cultural boundaries, details of royal officers, local rules, ethnic groups, land tenure, religious activities, beliefs, and trade and industries. Inscriptions are major assets to showcase inclusive of listed above, multitude information; hence, the benefits served by a study of high caliber, especially to the historical heritage research and to the heritage tourism. Several computer-aided solutions have been proposed to resolve the recognition of inscriptions in the Sri Lankan context. But this paper proposes an optimized classification. A dataset of five hundred images of original Sinhalese inscriptions dating from the 3rd century BC to the present was used to train and test the models. This study adopts four deep learning models to classify Sinhalese inscriptions: a newly proposed convolutional neural network model, and the pre-trained models Inception-v3, VGG-19, and ResNet-50. Palaeographical and morphological rules were adopted in the manual classification of Sinhalese inscriptions into a number of eras, namely, the Early Brahmi (3rd century BC to 1st century AD), Late Brahmi (2nd century AD to 4th century AD), Transitional Brahmi (5th century AD to 7th century AD), Medieval Sinhala (8th century AD to 14th century AD), and Modern Sinhala (15th century AD to the present). The results of the study indicate promising outcomes with accuracies of 70.66%, 85.94%, 57.44%, and 58.77% respectively for used four models. Further, the study revealed that the Inception-v3 model outperformed in classifying the Sinhalese inscriptions in respective eras.","PeriodicalId":17429,"journal":{"name":"Journal of the National Science Foundation of Sri Lanka","volume":"58 1","pages":"0"},"PeriodicalIF":0.4000,"publicationDate":"2023-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the National Science Foundation of Sri Lanka","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4038/jnsfsr.v51i3.11200","RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

A study of this caliber can be identified as a profound source for a wealth of knowledge as the aim of this study is to present chronological attribution of Sinhalese inscriptions based on deep learning approaches. Inscriptions shed light on a multitude of information such as chronicled civilizational thought, economic status, language evolution, cultural boundaries, details of royal officers, local rules, ethnic groups, land tenure, religious activities, beliefs, and trade and industries. Inscriptions are major assets to showcase inclusive of listed above, multitude information; hence, the benefits served by a study of high caliber, especially to the historical heritage research and to the heritage tourism. Several computer-aided solutions have been proposed to resolve the recognition of inscriptions in the Sri Lankan context. But this paper proposes an optimized classification. A dataset of five hundred images of original Sinhalese inscriptions dating from the 3rd century BC to the present was used to train and test the models. This study adopts four deep learning models to classify Sinhalese inscriptions: a newly proposed convolutional neural network model, and the pre-trained models Inception-v3, VGG-19, and ResNet-50. Palaeographical and morphological rules were adopted in the manual classification of Sinhalese inscriptions into a number of eras, namely, the Early Brahmi (3rd century BC to 1st century AD), Late Brahmi (2nd century AD to 4th century AD), Transitional Brahmi (5th century AD to 7th century AD), Medieval Sinhala (8th century AD to 14th century AD), and Modern Sinhala (15th century AD to the present). The results of the study indicate promising outcomes with accuracies of 70.66%, 85.94%, 57.44%, and 58.77% respectively for used four models. Further, the study revealed that the Inception-v3 model outperformed in classifying the Sinhalese inscriptions in respective eras.
使用深度学习方法的僧伽罗文铭文的时间归属
这种水平的研究可以被认为是丰富知识的深刻来源,因为本研究的目的是基于深度学习方法呈现僧伽罗铭文的时间归属。碑文揭示了大量的信息,如记载的文明思想、经济地位、语言演变、文化边界、王室官员的细节、地方规则、民族、土地所有权、宗教活动、信仰、贸易和工业。铭文是展示的主要资产,包括上述所列的众多信息;因此,高水平的研究对历史遗产研究和遗产旅游有很大的好处。已经提出了几种计算机辅助解决办法来解决斯里兰卡文题字的识别问题。本文提出了一种优化的分类方法。从公元前3世纪到现在的500幅原始僧伽罗铭文图像的数据集被用来训练和测试模型。本研究采用四种深度学习模型对僧伽罗文碑文进行分类:一种新提出的卷积神经网络模型,以及预训练模型Inception-v3、VGG-19和ResNet-50。古地学和形态学的规则被采用在手工分类僧伽罗铭文的几个时代,即早期婆罗米(公元前3世纪至公元1世纪),后期婆罗米(公元2世纪至公元4世纪),过渡婆罗米(公元5世纪至公元7世纪),中世纪僧伽罗(公元8世纪至公元14世纪)和现代僧伽罗(公元15世纪至今)。研究结果表明,四种模型的准确率分别为70.66%、85.94%、57.44%和58.77%。此外,研究还发现,Inception-v3模型在对各自时代的僧伽罗文进行分类方面表现优异。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
0.90
自引率
0.00%
发文量
57
审稿时长
>12 weeks
期刊介绍: The Journal of National Science Foundation of Sri Lanka (JNSF) publishes the results of research in Science and Technology. The journal is released four times a year, in March, June, September and December. This journal contains Research Articles, Reviews, Research Communications and Correspondences. Manuscripts submitted to the journal are accepted on the understanding that they will be reviewed prior to acceptance and that they have not been submitted for publication elsewhere.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信