Abstract:This paper presents an ontology created for classifying and researching material culture and its visual representations, that forms a part of an emerging data-driven research framework on Neoclassicism (ca. 1760-1860). The framework, named Neoclassica, unites a topdown approach to knowledge discovery, represented by the Neoclassicaontology, with innovative methods and techniques for processing multimodal data corresponding with a bottom-up approach. Below we will first describe the Neoclassica framework, discu… Show more
“…A detailed analysis has many facets in the DH and explores different features. An analysis is carried out of the visual features of the furniture and its relation to metadata in an ontology [9]. Gesture and posture analysis within figures in art has been explored by [19].…”
Section: Applications Of Image Processing In Digital Humanitiesmentioning
Printing technology has evolved through the past centuries due to technological progress. Within Digital Humanities, images are playing a more prominent role in research. For mass analysis of digitized historical images, bias can be introduced in various ways. One of them is the printing technology originally used. The classification of images to their printing technology e.g. woodcut, copper engraving, or lithography requires highly skilled experts. We have developed a deep learning classification system that achieves very good results. This paper explains the challenges of digitized collections for this task. To overcome them and to achieve good performance, shallow networks and appropriate sampling strategies needed to be combined. We also show how class activation maps (CAM) can be used to analyze the results.
“…A detailed analysis has many facets in the DH and explores different features. An analysis is carried out of the visual features of the furniture and its relation to metadata in an ontology [9]. Gesture and posture analysis within figures in art has been explored by [19].…”
Section: Applications Of Image Processing In Digital Humanitiesmentioning
Printing technology has evolved through the past centuries due to technological progress. Within Digital Humanities, images are playing a more prominent role in research. For mass analysis of digitized historical images, bias can be introduced in various ways. One of them is the printing technology originally used. The classification of images to their printing technology e.g. woodcut, copper engraving, or lithography requires highly skilled experts. We have developed a deep learning classification system that achieves very good results. This paper explains the challenges of digitized collections for this task. To overcome them and to achieve good performance, shallow networks and appropriate sampling strategies needed to be combined. We also show how class activation maps (CAM) can be used to analyze the results.
“…The Neoclassica research framework (Donig et al, 2016) was conceived to provide scholars with new instruments and methods for analyzing and classifying artifacts and aesthetic forms from the era of Classicism (ca. 1760Classicism (ca.…”
Section: The Neoclassica Research Frameworkmentioning
confidence: 99%
“…A data-driven bottom-up research routine in the Neoclassica research framework is the main use-case. This research framework is described more extensively by Donig et al [2]. It strives to deliver tools for analyzing the spread of aesthetic forms which are considered as a cultural transfer process.…”
Classifying aesthetic forms -a methodology at the heart of art historyThe transformation of aesthetic styles has been at the heart of art history since its inception as a scholarly discipline in the late eighteenth century. Analyzing the single artifact and the carefully curated corpus have been the techniques for crafting hermeneutic understanding for such processes of change. Recently new instruments based on statistical techniques empower us for a fresh take on bodies of sources once disregarded as second tier complementary sources such as for instance very large corpora.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.