Abstract:ABSTRACT:Dunhuang Mogao Grottoes in western China is one of the most famous World Cultural Heritage Sites, known for its glorious Chinese Buddhist art spanning a period of 1,000 years. However, it has been suffering from damage and degradation caused by man-made and natural factors. In this article, we present a novel line-drawing enhanced interactive system for digital restoration of damaged murals in Mogao Grottoes. Our system consists of four components, namely data pre-processing, damaged area selection, l… Show more
“…The results show that the damaged murals can be repaired better by using the repair model in this study. By comparing the model constructed in this study with the method in Fu et al, 12 the predicted value of the repair model in this study is closer to the true value. Moreover, in the similarity rate, by comparing the number of training samples with the difference of smoothing parameter d, it is found that when the value of d is small, the number of training samples should be increased to promote the accuracy of the prediction value.…”
Section: Discussionmentioning
confidence: 50%
“…Although the repair model constructed in this study is superior to the method in literature, 12 it takes a long time to implement the efficiency, which is due to the time spent in collecting similar sample materials. By choosing the parameters of the smoothing operator in this study, the influence of the smoothing operator on the predicted value is judged by the step size of 0.01, as shown in Figure 7.…”
Section: Repair Process Of Dunhuang Muralsmentioning
confidence: 97%
“…achieve satisfactory repair effect without increasing the user burden. 12 Esteve et al studied the restoration of church element murals and captured their geometric shape and development according to architectural elements. A new method based on differential correction is proposed and applied to the development of Juan's Church in Los Angeles, Valencia, Spain.…”
In this research, Dunhuang murals is taken as the object of restoration, and the role of digital repair combined with deep learning algorithm in mural restoration is explored. First, the image restoration technology is described, as well as its advantages and disadvantages are analyzed. Second, the deep learning algorithm based on artificial neural network is described and analyzed. Finally, the deep learning algorithm is integrated into the digital repair technology, and a mural restoration method based on the generalized regression neural network is proposed. The morphological expansion method and anisotropic diffusion method are used to preprocess the image. The MATLAB software is used for the simulation analysis and evaluation of the image restoration effect. The results show that in the restoration of the original image, the accuracy of the digital image restoration technology is not high. The nontexture restoration technology is not applicable in the repair of large-scale texture areas. The predicted value of the mural restoration effect based on the generalized neural network is closer to the true value. The anisotropic diffusion method has a significant effect on the processing of image noise. In the image similarity rate, the different number of training samples and smoothing parameters are compared and analyzed. It is found that when the value of δ is small, the number of training samples should be increased to improve the accuracy of the prediction value. If the number of training samples is small, a larger value of δ is needed to get a better prediction effect, and the best restoration effect is obtained for the restored image. Through this study, it is found that this study has a good effect on the restoration model of Dunhuang murals. It provides experimental reference for the restoration of later murals.
“…The results show that the damaged murals can be repaired better by using the repair model in this study. By comparing the model constructed in this study with the method in Fu et al, 12 the predicted value of the repair model in this study is closer to the true value. Moreover, in the similarity rate, by comparing the number of training samples with the difference of smoothing parameter d, it is found that when the value of d is small, the number of training samples should be increased to promote the accuracy of the prediction value.…”
Section: Discussionmentioning
confidence: 50%
“…Although the repair model constructed in this study is superior to the method in literature, 12 it takes a long time to implement the efficiency, which is due to the time spent in collecting similar sample materials. By choosing the parameters of the smoothing operator in this study, the influence of the smoothing operator on the predicted value is judged by the step size of 0.01, as shown in Figure 7.…”
Section: Repair Process Of Dunhuang Muralsmentioning
confidence: 97%
“…achieve satisfactory repair effect without increasing the user burden. 12 Esteve et al studied the restoration of church element murals and captured their geometric shape and development according to architectural elements. A new method based on differential correction is proposed and applied to the development of Juan's Church in Los Angeles, Valencia, Spain.…”
In this research, Dunhuang murals is taken as the object of restoration, and the role of digital repair combined with deep learning algorithm in mural restoration is explored. First, the image restoration technology is described, as well as its advantages and disadvantages are analyzed. Second, the deep learning algorithm based on artificial neural network is described and analyzed. Finally, the deep learning algorithm is integrated into the digital repair technology, and a mural restoration method based on the generalized regression neural network is proposed. The morphological expansion method and anisotropic diffusion method are used to preprocess the image. The MATLAB software is used for the simulation analysis and evaluation of the image restoration effect. The results show that in the restoration of the original image, the accuracy of the digital image restoration technology is not high. The nontexture restoration technology is not applicable in the repair of large-scale texture areas. The predicted value of the mural restoration effect based on the generalized neural network is closer to the true value. The anisotropic diffusion method has a significant effect on the processing of image noise. In the image similarity rate, the different number of training samples and smoothing parameters are compared and analyzed. It is found that when the value of δ is small, the number of training samples should be increased to improve the accuracy of the prediction value. If the number of training samples is small, a larger value of δ is needed to get a better prediction effect, and the best restoration effect is obtained for the restored image. Through this study, it is found that this study has a good effect on the restoration model of Dunhuang murals. It provides experimental reference for the restoration of later murals.
“…The Dunhuang murals are of great research value, especially for the study of religion, class relations, costumes, architecture and humanistic tales from different periods (such as Zhang Qian's Diplomatic Missions [张骞出使西域]) (Hu, 1993). In past research studies, taking the Dunhuang murals as objects of restoration, the role of digital repair combined with deep learning algorithms in the mural restoration was explored (She, 2020), and the line-drawing enhanced interactive system for the Dunhuang mural restoration was built (Fu et al, 2017). An improved inpainting algorithm for repairing the Dunhuang murals was proposed, and it obtained good visual effects, as well as improved objective evaluation EL 40,3 values, such as the peak signal-to-noise ratio of the image (Chen et al, 2020a(Chen et al, , 2020b.…”
Section: Literature Review 21 Dunhuang Cultural Heritagementioning
Purpose
Dunhuang murals are rich in cultural and artistic value. The purpose of this paper is to construct a novel mobile visual search (MVS) framework for Dunhuang murals, enabling users to efficiently search for similar, relevant and diversified images.
Design/methodology/approach
The convolutional neural network (CNN) model is fine-tuned in the data set of Dunhuang murals. Image features are extracted through the fine-tuned CNN model, and the similarities between different candidate images and the query image are calculated by the dot product. Then, the candidate images are sorted by similarity, and semantic labels are extracted from the most similar image. Ontology semantic distance (OSD) is proposed to match relevant images using semantic labels. Furthermore, the improved DivScore is introduced to diversify search results.
Findings
The results illustrate that the fine-tuned ResNet152 is the best choice to search for similar images at the visual feature level, and OSD is the effective method to search for the relevant images at the semantic level. After re-ranking based on DivScore, the diversification of search results is improved.
Originality/value
This study collects and builds the Dunhuang mural data set and proposes an effective MVS framework for Dunhuang murals to protect and inherit Dunhuang cultural heritage. Similar, relevant and diversified Dunhuang murals are searched to meet different demands.
“…Gao [46] proposed a virtual restoration method based on minimum spanning trees to restore mural color. Fu et al [47] proposed a novel enhanced white-out interactive system for mural image restoration. Zhou et al [48] proposed an intelligent restoration technique for digital images of murals based on machine learning algorithms.…”
Located in Dunhuang, northwest China, the Mogao Grottoes are a cultural treasure of China and the world. However, after more than 2,000 years of weathering and destruction, many murals faded and were damaged. This treasure of human art is in danger. Mural inpainting through deep learning can permanently preserve mural information. In order to reduce manpower and material resources, the efficiency of mural image restoration is significantly improved. Therefore, a digital restoration method combining Deformable Convolution (DCN), ECANet, ResNet and Cycle Generative Adversarial Network (CycleGAN) is proposed. We name it DC-CycleGAN. Compared with other image digital inpainting methods, the proposed DC-CycleGAN based mural image color inpainting method has better inpainting effects and higher model performance, which can better capture the high-frequency characteristics of the image and avoid network degradation and gradient disappearance. The digital restoration of mural images provides a new theoretical and scientific basis for the protection and restoration process of murals, and shows the latest attempts of mural restoration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.