A New Baseline for Feature Description on Multimodal Imaging of Paintings

Simple item page
dc.contributor.authorToorn, Jules van deren_US
dc.contributor.authorWiersma, Rubenen_US
dc.contributor.authorVandivere, Abbieen_US
dc.contributor.authorMarroquim, Ricardoen_US
dc.contributor.authorEisemann, Elmaren_US
dc.contributor.editorPonchio, Federicoen_US
dc.contributor.editorPintus, Ruggeroen_US
dc.date.accessioned2022-09-26T09:59:52Z
dc.date.available2022-09-26T09:59:52Z
dc.date.issued2022
dc.description.abstractMultimodal imaging is used by conservators and scientists to study the composition of paintings. To aid the combined analysis of these digitisations, such images must first be aligned. Rather than proposing a new domain-specific descriptor, we explore and evaluate how existing feature descriptors from related fields can improve the performance of feature-based painting digitisation registration. We benchmark these descriptors on pixel-precise, manually aligned digitisations of ''Girl with a Pearl Earring'' by Johannes Vermeer (c. 1665, Mauritshuis) and of ''18th-Century Portrait of a Woman''. As a baseline we compare against the well-established classical SIFT descriptor. We consider two recent descriptors: the handcrafted multimodal MFD descriptor, and the learned unimodal SuperPoint descriptor. Experiments show that SuperPoint starkly increases description matching accuracy by 40% for modalities with little modality-specific artefacts. Further, performing craquelure segmentation and using the MFD descriptor results in significant description matching accuracy improvements for modalities with many modalityspecific artefacts.en_US
dc.description.sectionheadersSession 3
dc.description.seriesinformationEurographics Workshop on Graphics and Cultural Heritage
dc.identifier.doi10.2312/gch.20221223
dc.identifier.isbn978-3-03868-178-6
dc.identifier.issn2312-6124
dc.identifier.pages45-53
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/gch.20221223
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/gch20221223
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies --> Image processing; Applied computing --> Fine arts
dc.subjectComputing methodologies
dc.subjectImage processing
dc.subjectApplied computing
dc.subjectFine arts
dc.titleA New Baseline for Feature Description on Multimodal Imaging of Paintingsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
045-053.pdf
Size:
23.06 MB
Format:
Adobe Portable Document Format
Download
Collections
GCH 2022 - Eurographics Workshop on Graphics and Cultural Heritage