中世纪远观是否可能:利用视觉分析扩展和丰富传统图像收藏的注释内容

IF 0.7 3区 文学 0 HUMANITIES, MULTIDISCIPLINARY
Christofer Meinecke, Estelle Guéville, David Joseph Wrisley, Stefan Jänicke
{"title":"中世纪远观是否可能:利用视觉分析扩展和丰富传统图像收藏的注释内容","authors":"Christofer Meinecke, Estelle Guéville, David Joseph Wrisley, Stefan Jänicke","doi":"10.1093/llc/fqae020","DOIUrl":null,"url":null,"abstract":"Distant viewing approaches have typically used image datasets close to the contemporary image data used to train machine learning models. To work with images from other historical periods requires expert annotated data, and the quality of labels is crucial for the quality of results. Especially when working with cultural heritage collections that contain myriad uncertainties, annotating data, or re-annotating, legacy data is an arduous task. In this paper, we describe working with two pre-annotated sets of medieval manuscript images that exhibit conflicting and overlapping metadata. Since a manual reconciliation of the two legacy ontologies would be very expensive, we aim (1) to create a more uniform set of descriptive labels to serve as a “bridge” in the combined dataset, and (2) to establish a high-quality hierarchical classification that can be used as a valuable input for subsequent supervised machine learning. To achieve these goals, we developed visualization and interaction mechanisms, enabling medievalists to combine, regularize and extend the vocabulary used to describe these, and other cognate, image datasets. The visual interfaces provide experts an overview of relationships in the data going beyond the sum total of the metadata. Word and image embeddings as well as co-occurrences of labels across the datasets enable batch re-annotation of images, recommendation of label candidates, and support composing a hierarchical classification of labels.","PeriodicalId":45315,"journal":{"name":"Digital Scholarship in the Humanities","volume":null,"pages":null},"PeriodicalIF":0.7000,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Is medieval distant viewing possible? : Extending and enriching annotation of legacy image collections using visual analytics\",\"authors\":\"Christofer Meinecke, Estelle Guéville, David Joseph Wrisley, Stefan Jänicke\",\"doi\":\"10.1093/llc/fqae020\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Distant viewing approaches have typically used image datasets close to the contemporary image data used to train machine learning models. To work with images from other historical periods requires expert annotated data, and the quality of labels is crucial for the quality of results. Especially when working with cultural heritage collections that contain myriad uncertainties, annotating data, or re-annotating, legacy data is an arduous task. In this paper, we describe working with two pre-annotated sets of medieval manuscript images that exhibit conflicting and overlapping metadata. Since a manual reconciliation of the two legacy ontologies would be very expensive, we aim (1) to create a more uniform set of descriptive labels to serve as a “bridge” in the combined dataset, and (2) to establish a high-quality hierarchical classification that can be used as a valuable input for subsequent supervised machine learning. To achieve these goals, we developed visualization and interaction mechanisms, enabling medievalists to combine, regularize and extend the vocabulary used to describe these, and other cognate, image datasets. The visual interfaces provide experts an overview of relationships in the data going beyond the sum total of the metadata. Word and image embeddings as well as co-occurrences of labels across the datasets enable batch re-annotation of images, recommendation of label candidates, and support composing a hierarchical classification of labels.\",\"PeriodicalId\":45315,\"journal\":{\"name\":\"Digital Scholarship in the Humanities\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2024-04-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Digital Scholarship in the Humanities\",\"FirstCategoryId\":\"98\",\"ListUrlMain\":\"https://doi.org/10.1093/llc/fqae020\",\"RegionNum\":3,\"RegionCategory\":\"文学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"0\",\"JCRName\":\"HUMANITIES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital Scholarship in the Humanities","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1093/llc/fqae020","RegionNum":3,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"HUMANITIES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

远观方法通常使用与当代图像数据接近的图像数据集来训练机器学习模型。要处理其他历史时期的图像,需要专家注释数据,而标签的质量对结果的质量至关重要。尤其是在处理包含无数不确定因素的文化遗产藏品时,对数据进行注释或重新注释遗留数据是一项艰巨的任务。在本文中,我们介绍了如何处理两套预先标注的中世纪手稿图像,这两套图像的元数据存在冲突和重叠。由于手动调节两个遗留本体论的成本非常高昂,我们的目标是:(1) 创建一套更统一的描述性标签,作为合并数据集的 "桥梁";(2) 建立高质量的分层分类,作为后续监督机器学习的宝贵输入。为了实现这些目标,我们开发了可视化和交互机制,使中世纪学者能够组合、规范和扩展用于描述这些以及其他同类图像数据集的词汇。可视化界面为专家们提供了超越元数据总和的数据关系概览。单词和图像嵌入以及数据集中标签的共现可以实现图像的批量重新标注、推荐候选标签,并支持对标签进行分层分类。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Is medieval distant viewing possible? : Extending and enriching annotation of legacy image collections using visual analytics
Distant viewing approaches have typically used image datasets close to the contemporary image data used to train machine learning models. To work with images from other historical periods requires expert annotated data, and the quality of labels is crucial for the quality of results. Especially when working with cultural heritage collections that contain myriad uncertainties, annotating data, or re-annotating, legacy data is an arduous task. In this paper, we describe working with two pre-annotated sets of medieval manuscript images that exhibit conflicting and overlapping metadata. Since a manual reconciliation of the two legacy ontologies would be very expensive, we aim (1) to create a more uniform set of descriptive labels to serve as a “bridge” in the combined dataset, and (2) to establish a high-quality hierarchical classification that can be used as a valuable input for subsequent supervised machine learning. To achieve these goals, we developed visualization and interaction mechanisms, enabling medievalists to combine, regularize and extend the vocabulary used to describe these, and other cognate, image datasets. The visual interfaces provide experts an overview of relationships in the data going beyond the sum total of the metadata. Word and image embeddings as well as co-occurrences of labels across the datasets enable batch re-annotation of images, recommendation of label candidates, and support composing a hierarchical classification of labels.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
1.80
自引率
25.00%
发文量
78
期刊介绍: DSH or Digital Scholarship in the Humanities is an international, peer reviewed journal which publishes original contributions on all aspects of digital scholarship in the Humanities including, but not limited to, the field of what is currently called the Digital Humanities. Long and short papers report on theoretical, methodological, experimental, and applied research and include results of research projects, descriptions and evaluations of tools, techniques, and methodologies, and reports on work in progress. DSH also publishes reviews of books and resources. Digital Scholarship in the Humanities was previously known as Literary and Linguistic Computing.
×
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