What's wrong with the murals at the Mogao Grottoes: a near-infrared hyperspectral imaging method

Meijun Sun, Dong Zhang, Zheng Wang, Jinchang Ren, Bolong Chai, Jizhou Sun

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Although a significant amount of work has been performed to preserve the ancient murals in the Mogao Grottoes by Dunhuang Cultural Research, non-contact methods need to be developed to effectively evaluate the degree of flaking of the murals. In this study, we propose to evaluate the flaking by automatically analyzing hyperspectral images that were scanned at the site. Murals with various degrees of flaking were scanned in the 126th cave using a near-infrared (NIR) hyperspectral camera with a spectral range of approximately 900 to 1700 nm. The regions of interest (ROIs) of the murals were manually labeled and grouped into four levels: normal, slight, moderate, and severe. The average spectral data from each ROI and its group label were used to train our classification model. To predict the degree of flaking, we adopted four algorithms: deep belief networks (DBNs), partial least squares regression (PLSR), principal component analysis with a support vector machine (PCA + SVM) and principal component analysis with an artificial neural network (PCA + ANN). The experimental results show the effectiveness of our method. In particular, better results are obtained using DBNs when the training data contain a significant amount of striping noise.

LanguageEnglish
Article number14371
Number of pages10
JournalScientific Reports
Volume5
DOIs
Publication statusPublished - 23 Sep 2015

Fingerprint

Infrared imaging
Bayesian networks
Principal component analysis
Caves
Support vector machines
Labels
Cameras
Infrared radiation
Neural networks
Hyperspectral imaging

Keywords

  • hyperspectral imaging
  • ancient murals

Cite this

Sun, Meijun ; Zhang, Dong ; Wang, Zheng ; Ren, Jinchang ; Chai, Bolong ; Sun, Jizhou. / What's wrong with the murals at the Mogao Grottoes : a near-infrared hyperspectral imaging method. In: Scientific Reports. 2015 ; Vol. 5.
@article{f18b233f6dea4bbaafc1c222af64503a,
title = "What's wrong with the murals at the Mogao Grottoes: a near-infrared hyperspectral imaging method",
abstract = "Although a significant amount of work has been performed to preserve the ancient murals in the Mogao Grottoes by Dunhuang Cultural Research, non-contact methods need to be developed to effectively evaluate the degree of flaking of the murals. In this study, we propose to evaluate the flaking by automatically analyzing hyperspectral images that were scanned at the site. Murals with various degrees of flaking were scanned in the 126th cave using a near-infrared (NIR) hyperspectral camera with a spectral range of approximately 900 to 1700 nm. The regions of interest (ROIs) of the murals were manually labeled and grouped into four levels: normal, slight, moderate, and severe. The average spectral data from each ROI and its group label were used to train our classification model. To predict the degree of flaking, we adopted four algorithms: deep belief networks (DBNs), partial least squares regression (PLSR), principal component analysis with a support vector machine (PCA + SVM) and principal component analysis with an artificial neural network (PCA + ANN). The experimental results show the effectiveness of our method. In particular, better results are obtained using DBNs when the training data contain a significant amount of striping noise.",
keywords = "hyperspectral imaging, ancient murals",
author = "Meijun Sun and Dong Zhang and Zheng Wang and Jinchang Ren and Bolong Chai and Jizhou Sun",
year = "2015",
month = "9",
day = "23",
doi = "10.1038/srep14371",
language = "English",
volume = "5",
journal = "Scientific Reports",
issn = "2045-2322",

}

What's wrong with the murals at the Mogao Grottoes : a near-infrared hyperspectral imaging method. / Sun, Meijun; Zhang, Dong; Wang, Zheng; Ren, Jinchang; Chai, Bolong; Sun, Jizhou.

In: Scientific Reports, Vol. 5, 14371 , 23.09.2015.

Research output: Contribution to journalArticle

TY - JOUR

T1 - What's wrong with the murals at the Mogao Grottoes

T2 - Scientific Reports

AU - Sun, Meijun

AU - Zhang, Dong

AU - Wang, Zheng

AU - Ren, Jinchang

AU - Chai, Bolong

AU - Sun, Jizhou

PY - 2015/9/23

Y1 - 2015/9/23

N2 - Although a significant amount of work has been performed to preserve the ancient murals in the Mogao Grottoes by Dunhuang Cultural Research, non-contact methods need to be developed to effectively evaluate the degree of flaking of the murals. In this study, we propose to evaluate the flaking by automatically analyzing hyperspectral images that were scanned at the site. Murals with various degrees of flaking were scanned in the 126th cave using a near-infrared (NIR) hyperspectral camera with a spectral range of approximately 900 to 1700 nm. The regions of interest (ROIs) of the murals were manually labeled and grouped into four levels: normal, slight, moderate, and severe. The average spectral data from each ROI and its group label were used to train our classification model. To predict the degree of flaking, we adopted four algorithms: deep belief networks (DBNs), partial least squares regression (PLSR), principal component analysis with a support vector machine (PCA + SVM) and principal component analysis with an artificial neural network (PCA + ANN). The experimental results show the effectiveness of our method. In particular, better results are obtained using DBNs when the training data contain a significant amount of striping noise.

AB - Although a significant amount of work has been performed to preserve the ancient murals in the Mogao Grottoes by Dunhuang Cultural Research, non-contact methods need to be developed to effectively evaluate the degree of flaking of the murals. In this study, we propose to evaluate the flaking by automatically analyzing hyperspectral images that were scanned at the site. Murals with various degrees of flaking were scanned in the 126th cave using a near-infrared (NIR) hyperspectral camera with a spectral range of approximately 900 to 1700 nm. The regions of interest (ROIs) of the murals were manually labeled and grouped into four levels: normal, slight, moderate, and severe. The average spectral data from each ROI and its group label were used to train our classification model. To predict the degree of flaking, we adopted four algorithms: deep belief networks (DBNs), partial least squares regression (PLSR), principal component analysis with a support vector machine (PCA + SVM) and principal component analysis with an artificial neural network (PCA + ANN). The experimental results show the effectiveness of our method. In particular, better results are obtained using DBNs when the training data contain a significant amount of striping noise.

KW - hyperspectral imaging

KW - ancient murals

UR - http://www.scopus.com/inward/record.url?scp=84942456142&partnerID=8YFLogxK

U2 - 10.1038/srep14371

DO - 10.1038/srep14371

M3 - Article

VL - 5

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 14371

ER -