In the field of Cultural Heritage, image analysis represents an indispensable practice for restorers to collect information about the state of preservation of monuments and artifacts and plan restoration interventions. In addition, during the last two decades, the wide spread of remote sensing technologies and the possibility to build 3D reality-based models of artifacts allow the extension of image analysis to 3D environments. In this context, the purpose of this contribution is to show the results of investigations held in order to provide a methodology for the automatic detection of deteriorated areas within architectures and artifacts using colour images as a field of examination. Using both 2D and 3D segmentation approaches, our methodology aims at speeding and efficiently performing the automatic detection of deteriorated zones within Cultural Heritage and therefore segment 3D digital models acquired using different survey technologies. Within our investigations, we selected case studies concerning recurrent deteriorations, such as, for example, detachments, cracks and chromatic alterations; we run them both to manual and to automatic recognition and selection tests, in order to compare the results obtained using these approaches and evaluate the reliability of the automatic one. Results comparison included computational and user time, quantification of the deteriorated area error between manual and automatically detected zones. Additional parameters characterizing the specific type of deteriorations were also computed for each case study. Comparison between the automatic and the manual procedure showed that the automatic detection is faster and reliable in all our selected case studies, with evident improvements in the efficient evaluation of the entity and extension of deteriorated areas on 3D geometry.

An integrated and automated segmentation approach to deteriorated regions recognition on 3D reality-based models of cultural heritage artifacts

MANFERDINI, ANNA MARIA;BARONCINI, VALENTINA;CORSI, CRISTIANA
2012

Abstract

In the field of Cultural Heritage, image analysis represents an indispensable practice for restorers to collect information about the state of preservation of monuments and artifacts and plan restoration interventions. In addition, during the last two decades, the wide spread of remote sensing technologies and the possibility to build 3D reality-based models of artifacts allow the extension of image analysis to 3D environments. In this context, the purpose of this contribution is to show the results of investigations held in order to provide a methodology for the automatic detection of deteriorated areas within architectures and artifacts using colour images as a field of examination. Using both 2D and 3D segmentation approaches, our methodology aims at speeding and efficiently performing the automatic detection of deteriorated zones within Cultural Heritage and therefore segment 3D digital models acquired using different survey technologies. Within our investigations, we selected case studies concerning recurrent deteriorations, such as, for example, detachments, cracks and chromatic alterations; we run them both to manual and to automatic recognition and selection tests, in order to compare the results obtained using these approaches and evaluate the reliability of the automatic one. Results comparison included computational and user time, quantification of the deteriorated area error between manual and automatically detected zones. Additional parameters characterizing the specific type of deteriorations were also computed for each case study. Comparison between the automatic and the manual procedure showed that the automatic detection is faster and reliable in all our selected case studies, with evident improvements in the efficient evaluation of the entity and extension of deteriorated areas on 3D geometry.
Manferdini A.M.; Baroncini V.; Corsi C.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11585/120971
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 6
social impact