Analysis of craquelure patterns in historical painting using image processing along with neural network algorithms

Zabari, Noemi (2021) Analysis of craquelure patterns in historical painting using image processing along with neural network algorithms. In: SPIE Optical Metrology, 2021, online. [Document issu d'une conférence ou d'un atelier]

Prévisualisation

PDF published.pdf Download (4MB) | Prévisualisation

Résumé (en anglais)

Recent advances in technology have brought major breakthroughs in deep learning techniques. In this work, the author will elaborate on such techniques for output data of image processing performed on craquelure patterns in historical paintings. Historical painted objects, especially panel paintings, with their long environmental history, exhibit complex crack patterns called craquelures. These are cracks in paintings that can be referred to as ‘edge fractures’ since they are formed from the free surface. The analysis has been conducted on the set of selected craquelure patterns to which a recent deep learning method, i.e. Neural Networks algorithm is implemented and the results of such a self-learning process are discussed.

Type:	Document issu d'une conférence ou d'un atelier (Article)
Auteurs:	Auteurs E-mail Zabari, Noemi noemi.zabari@ikifp.edu.pl
Langues:	Anglais
Mots-clés libres:	Craquelures; Neural Networks; paintings
Sujets:	E.CONSERVATION ET RESTAURATION > 01. Généralités E.CONSERVATION ET RESTAURATION > 12. Techniques E.CONSERVATION ET RESTAURATION > 08. Suivi F.TECHNIQUES SCIENTIFIQUES ET METHODOLOGIES DE CONSERVATION > 06. Analyse des matériaux F.TECHNIQUES SCIENTIFIQUES ET METHODOLOGIES DE CONSERVATION > 43. Analyse Quantitative
Déposé par:	Mrs Noemi Zabari
Date de dépôt:	02 décembre 2021 22:03
Dernière modification:	02 décembre 2021 22:03
URI:	https://openarchive.icomos.org/id/eprint/2518

Actions (login required)

Fiche du document

Metadata

• HTML Citation
• ASCII Citation
• Full
• OpenURL ContextObject
• EndNote
• BibTeX
• MODS
• MPEG-21 DIDL
• EP3 XML
• Dublin Core
• Reference Manager
• Eprints Application Profile
• Simple Metadata
• Refer
• METS

Downloads