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}
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.
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.