Murals unearthed in China have outstanding regional characteristics and one of the largest period spans in scale and variety. To explore the visual distinguishability and topic autocorrelation of murals unearthed in China from the spatial perspective, multiple classification models are employed to classify murals unearthed in China through visual features. Then, the k-means is employed to mine topics, and they are analysed through topic intensities (TIs), Moran’s Index (MI) and spatial topic concentration degrees (STCDs). In addition, the characteristics of topic distribution and evolution are summarised and revealed in the spatial dimension. From a spatial perspective, it verifies the distinguishability of visual features of murals through ViT_BOW_GNB, and the precision of this model is 98.17%. Thirteen topics are clustered through k-means, and the distribution of mural topics is spatial autocorrelation according to MI. Besides, the topic evolves from the political centre to the surrounding area, and the topics with high intensities are highly concentrated in spatial. This study reveals the spatial characteristics of the mural at the level of visual features and semantics, which facilitates the digital management, conservation and knowledge discovery of cultural heritage resources.
Dal FovoAMazzinghiAOmariniS, et al. Non-invasive mapping methods for pigments analysis of Roman mural paintings. J Cult Herit2020; 43: 311–318.
2.
XuG. The complete collection of murals unearthed in China. Beijing, China: Science Press, 2011.
3.
YuTLinCZhangS, et al. Artificial intelligence for Dunhuang cultural heritage protection: the project and the dataset. Int J Comput Vis2022; 130(11): 2646–2673.
4.
CaoJZhangZZhaoA, et al. Ancient mural restoration based on a modified generative adversarial network. Herit Sci2020; 8(1): 1–14.
5.
TortoraMSfarraSChiariniM, et al. Non-destructive and micro-invasive testing techniques for characterizing materials, structures and restoration problems in mural paintings. Appl Surf Sci2016; 387: 971–985.
6.
ZhangFHuangXFangW, et al. Non-rigid registration of mural images and laser scanning data based on the optimization of the edges of interest. Sci China Inf Sci2013; 56(6): 1–10.
7.
KoenderinkJJVan DoornAJ. Affine structure from motion. J Opt Soc Am A1991; 8(2): 377–385.
8.
GuoJSongNWangX. The evaluation of approaches to Semantic description of Dunhuang frescoes digital images from the perspective of users. Doc Inf Knowl2018; 03: 66–77.
9.
ZengZSunSLiT, et al. Exploring the topic evolution of Dunhuang murals through image classification. J Inf Sci. Epub ahead of print 23February2022. DOI: 10.1177/01655515221074336.
10.
ZengZSunSLiT, et al. Mobile visual search model for Dunhuang murals in the smart library. Libr Hi Tech2022; 40(6): 1796–1818.
11.
LiuHWangX. The spatial attributes of art geography. Hum Geogr2004; 1: 58–61.
12.
WangXTanXGuiH, et al. A semantic enrichment approach to linking and enhancing Dunhuang cultural heritage data. In: GolubKLiuYH (eds) Information and knowledge organisation in digital humanities. London: Routledge, 2021, pp. 87–105.
13.
NiuJGaoY. The empowerment space and governance logic of ancient mural digitization technology – taking ancient Frescoes as the analysis center. J Henan Norm Univ2022; 49(04): 103–108.
14.
WangX. Study on image system of Chinese tomb mural. Natl Arts2014; 02: 38–44.
15.
JiangW. Commentary of Chinese fresco developing course. Bord Econ Cult2009; 05: 108–109.
16.
ZengZSunS. Research on mobile visual search model for Dunhuang murals. Inf Doc Serv2021; 42(02): 104–112.
17.
ZengZSunSSunJ, et al. Constructing a mobile visual search framework for Dunhuang murals based on fine-tuned CNN and ontology semantic distance. Electron Libr2022; 40(3): 121–139.
18.
LiY. Classification and recognition of ancient mural paintings in Sichuan based on color feature extraction. J Southwest Univ (Nat Sci Ed)2022; 44(05): 203–208.
19.
LyuSWangSHouM, et al. Extraction of mural paint loss diseases based on improved U-Net. Geomatics World2022; 29(01): 69–74.
20.
ChenYChenJAiY, et al. Mural image inpainting based on edge missing reconstruction and improved priority. Laser Optoelectron Prog2021; 58(24): 231–240.
21.
TanXLuoXWangX, et al. Representation and display of digital images of cultural heritage: a semantic enrichment approach. Knowl Organ2021; 48(3): 231–247.
22.
WangXChangWTanX. Representing and linking Dunhuang cultural heritage information resources using knowledge graph. Knowl Organ2021; 47(7): 604–615.
23.
WangXSongNZhangL, et al. Understanding subjects contained in Dunhuang mural images for deep semantic annotation. J Doc2018; 74(2): 333–353.
24.
ZhangM. Application of big data analysis technology in classification statistics of ancient tomb murals. In: CIBDA 2022; 3rd international conference on computer information and big data applications, Wuhan, China, 25–27 March 2022, pp. 1–7. Berlin: VDE.
25.
WangHLHanPHChenYM, et al. Dunhuang mural restoration using deep learning. In: SIGGRAPH Asia 2018 technical briefs, December2018, pp. 1–4. Tokyo Japan: ACM.
26.
LiXLuDPanY. Color restoration and image retrieval for Dunhuang fresco preservation. IEEE Multimed2000; 7(2): 38–42.
27.
LedermanDLampotangSShamirMY. Automatic endotracheal tube position confirmation system based on image classification–A preliminary assessment. Med Eng Phys2011; 33(8): 1017–1026.
28.
MittalPKansalMkaur JhajjH. Combined classifier for plant classification and identification from leaf image based on visual attributes. In 2018 International conference on intelligent circuits and systems (ICICS), 19–20April2018, pp. 184–187. New York: IEEE.
29.
JeyarajPRSamuel NadarER. Computer-assisted medical image classification for early diagnosis of oral cancer employing deep learning algorithm. J Cancer Res Clin Oncol2019; 145(4): 829–837.
30.
YuQWangCMcKennaF, et al. Rapid visual screening of soft-story buildings from street view images using deep learning classification. Earthq Eng Eng Vib2020; 19(4): 827–838.
31.
JebaraniWSLKamalaharidhariniT. Robust face recognition and classification system based on SIFT and DCP techniques in image processing. In: 2017 international conference on intelligent computing and control (I2C2), Coimbatore, India, 23–24 June 2017, pp. 1–8. New York: IEEE.
32.
JankovićR. Machine learning models for cultural heritage image classification: comparison based on attribute selection. Information2019; 11(1): 1–13.
CaoJYanMJiaY, et al. Application of a modified Inception-v3 model in the dynasty-based classification of ancient murals. EURASIP J Adv Signal Process2021; 2021(1): 1–25.
35.
LiuX. Art painting image classification based on neural network. Comput Intell Neurosci. Epub ahead of print4July2022. DOI: 10.1155/2022/3119604.
36.
WangTWangW. Research on a thangka image classification method based on support vector machine. Int J Pattern Recognit Artif Intell2019; 33(12): 1954030.
37.
MaJWangCYanL, et al. Analysis of patent technology topic evolution based on product life cycle. J China Soc Sci Tech Inf2022; 41(07): 684–691.
38.
YangHWangYZhangL. Technology prediction based on core patents technology topic recognition and evolution analysis. J Intell2022; 41(07): 49–56.
39.
LiangSLiuX. Research progress on topic evolution of scientific and technical literatures based on text mining. Libr Inf Serv2022; 66(13): 138–149.
40.
HeWFengGXieH. Analyzing scientific literature with content similarity-topic over time model. Data Anal Knowl Discov2018; 2(11): 64–72.
41.
ZhangYCaiXFryCV, et al. Topic evolution, disruption and resilience in early COVID-19 research. Scientometrics2021; 126(5): 4225–4253.
42.
ZhangWYaoREvansR, et al. Collaboration of issuing agencies and topic evolution of health informatisation policies in China. J Inf Sci. Epub ahead of print 24February2022. DOI: 10.1177/01655515221074323.
43.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. arXiv2014.
44.
DosovitskiyABeyerLKolesnikovA, et al. An image is worth 16x16 words: transformers for image recognition at scale. arXiv2014.
45.
LiY. Research and application of deep learning in image recognition. In: 2022 IEEE 2nd International conference on power, electronics and computer applications (ICPECA), Shenyang, China, 21–23 January 2022, pp. 994–999. New York: IEEE.
46.
KhanSNaseerMHayatM, et al. Transformers in vision: a survey. ACM Comput Surv2022; 54(10s): 1–41.
47.
RashidJShahSMAIrtazaA. An efficient topic modeling approach for text mining and information retrieval through K-means clustering. Mehran Univ Res J Eng Technol2020; 39(1): 213–222.
48.
ChenY. An analytical process of spatial autocorrelation functions based on Moran’s index. PLoS ONE2021; 16(4): e0249589.
49.
ToblerWR. A computer movie simulating urban growth in the Detroit region. Econ Geogr1970; 46(Suppl. 1): 234–240.
50.
MillerHJ. Tobler’s first law and spatial analysis. Ann Assoc Am Geogr2004; 94(2): 284–289.
51.
OrdJKGetisA. Local spatial autocorrelation statistics: distributional issues and an application. Geogr Anal1995; 27(4): 286–306.
