2019
DOI: 10.3390/app9173591
|View full text |Cite
|
Sign up to set email alerts
|

Extraction of Hidden Information under Sootiness on Murals Based on Hyperspectral Image Enhancement

Abstract: Changes in the environment and human activities can cause serious deterioration of murals. Hyperspectral imaging technology can observe murals in the range of visible to near infrared light, providing a scientific and non-destructive way for mural digital preservation. An effective method to extract hidden information from the sootiness of murals in order to enhance the visual value of patterns in ancient murals using hyperspectral imaging is proposed in this paper. Firstly, Minimum Noise Fraction transform wa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 18 publications
0
5
0
Order By: Relevance
“…Compared with the standard convolutional autoencoder, two improvements are made to the multi-scale residual attention autoencoder network. First, We consider incorporating manually designed prior information into the model to encourage the network to focus more on the hidden information features 2 . For example, removing the noisy bands after the minimum noise separation transform (MNF) and selecting the principal component bands with higher eigenvalues to be added to the network input.…”
Section: Multiscale Residual Autoencoder Networkmentioning
confidence: 99%
“…Compared with the standard convolutional autoencoder, two improvements are made to the multi-scale residual attention autoencoder network. First, We consider incorporating manually designed prior information into the model to encourage the network to focus more on the hidden information features 2 . For example, removing the noisy bands after the minimum noise separation transform (MNF) and selecting the principal component bands with higher eigenvalues to be added to the network input.…”
Section: Multiscale Residual Autoencoder Networkmentioning
confidence: 99%
“…It has a smaller size and is oriented to the right, although the anterior part practically coincides with the infraposition. On the left side there is a single tectiform in the shape of a slightly curved rectangle (4). The support has a very low degree of humidity, and the front part of the animal (especially the head) has a calcite coating.…”
Section: Working Areamentioning
confidence: 99%
“…In recent years,image processing as a nondestructive research technique [9][10][11] has achieved good effects in the field of cultural heritage conservation and intelligent restoration of cultural relics. Researchers can perform non-contact labeling of mural images with software such as AutoCAD and IDRISI.…”
Section: Introductionmentioning
confidence: 99%