This paper presents a tool targeted at archaeologists and cultural heritage operators. The tool assists the process of reconstructing broken pictorial artifacts from their physical fragments. The fragments are organized into a database indexed on features such as color distribution, shape and texture. The system can be queried using any fragment as the key, and the results are displayed from the most similar to the most dissimilar. The system provides the operator with complete workflow from photoacquisition onwards. The performance has been assessed with computer simulations and a real use case. Two of the simulations are discussed, as well as the real use case, based on an actual XV century fresco that needed reconstruction.
MOSAIC: Multi-object segmentation for assisted image reconstruction / Caggiano, Sonia; DE MARSICO, Maria; Distasi, Riccardo; Riccio, Daniel. - STAMPA. - 9493:(2015), pp. 282-299. (Intervento presentato al convegno 4th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2015 tenutosi a Lisbon; Portugal nel 2015) [10.1007/978-3-319-27677-9_18].
MOSAIC: Multi-object segmentation for assisted image reconstruction
DE MARSICO, Maria;
2015
Abstract
This paper presents a tool targeted at archaeologists and cultural heritage operators. The tool assists the process of reconstructing broken pictorial artifacts from their physical fragments. The fragments are organized into a database indexed on features such as color distribution, shape and texture. The system can be queried using any fragment as the key, and the results are displayed from the most similar to the most dissimilar. The system provides the operator with complete workflow from photoacquisition onwards. The performance has been assessed with computer simulations and a real use case. Two of the simulations are discussed, as well as the real use case, based on an actual XV century fresco that needed reconstruction.File | Dimensione | Formato | |
---|---|---|---|
Caggiano_MOSAIC_2015.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
3.04 MB
Formato
Adobe PDF
|
3.04 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.