From remote sensing and machine learning to the history of the Silk Road: large scale material identification on wall paintings
Autor: | Golnaz Shahtahmassebi, Andrei Lucian, Wenyuan Zhang, Sotiria Kogou, Bomin Su, Sam van Schaik, Biwen Shui, Haida Liang |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
media_common.quotation_subject
Optical spectroscopy lcsh:Medicine Machine learning computer.software_genre 01 natural sciences Article Imaging studies Techniques and instrumentation Cave 0601 history and archaeology Sanskrit lcsh:Science media_common geography Painting Multidisciplinary geography.geographical_feature_category 060102 archaeology business.industry 010401 analytical chemistry lcsh:R Imaging and sensing 06 humanities and the arts Art Reflectivity language.human_language 0104 chemical sciences Style (visual arts) Identification (information) Remote sensing (archaeology) language lcsh:Q Artificial intelligence business Scale (map) computer |
Zdroj: | Scientific Reports, Vol 10, Iss 1, Pp 1-14 (2020) Scientific Reports |
ISSN: | 2045-2322 |
Popis: | Automatic remote reflectance spectral imaging of large painted areas in high resolution, from distances of tens of meters, has made the imaging of entire architectural interior feasible. However, it has significantly increased the volume of data. Here we present a machine learning based method to automatically detect ‘hidden’ writings and map material variations. Clustering of reflectance spectra allowed materials at inaccessible heights to be properly identified by performing non-invasive analysis on regions in the same cluster at accessible heights using a range of complementary spectroscopic techniques. The world heritage site of the Mogao caves, along the ancient Silk Road, consists of 492 richly painted Buddhist cave temples dating from the fourth to fourteenth century. Cave 465 at the northern end of the site is unique in its Indo-Tibetan tantric Buddhist style, and like many other caves, the date of its construction is still under debate. This study demonstrates the powers of an interdisciplinary approach that combines material identification, palaeographic analysis of the revealed Sanskrit writings and archaeological evidence for the dating of the cave temple paintings, narrowing it down to the late twelfth century to thirteenth century. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |