Construction and Retrieval of Shu Brocade Pattern Image Resources for Digital Preservation
DOI: https://doi.org/10.62517/jbdc.202601406
Author(s)
Xuan Lu1, Zhicong Rui2, Xingren Wang1
Affiliation(s)
1Key Laboratory of Digital Preservation and Transmission of Weaving and Embroidery Heritage, Sichuan Provincial Department of Culture and Tourism (Chengdu Qinggong Polytechnic University), Sichuan Provincial Department of Culture and Tourism, Chengdu, Sichuan, China
2Sichuan Engineering Research Center for Functional Development and Application of High-Performance Specialty Textile Materials, Chengdu, Sichuan, China
Abstract
The government currently places great emphasis on the digital preservation of intangible cultural heritage, and given that Shu brocade is renowned throughout the country, the digital archiving of its patterns is of utmost importance. Addressing issues such as the lack of domain-specific image classification models for Shu brocade patterns, scarcity of data, and insufficient digital preservation of related cultural heritage, this study established a software-based digital platform using over 230 images of Shu brocade patterns as a foundation. At the same time, it carried out research on resource indexing and pattern classification uses for the Shu brocade pattern database. It built a searchable pattern database. This database arranges images by names, descriptions, themes, and other metadata. It also allows keyword searches and category-based filtering. To develop a lightweight Shu Brocade model, it used the ImageNet-pretrained Swin Transformer Tiny model. This model carried out classification analysis on a small dataset. The dataset had 113 images. The chosen model reached a validation accuracy of 85.71%. Its test accuracy was 53.33%. These results gave preliminary findings for the classification of Shu brocade patterns. The results indicate that the lack of category samples and distribution imbalances limited the accuracy of classification predictions. Further training requires more images and better coverage of all classes.
Keywords
Shu Brocade Patterns; Digital Preservation; Resource Organization; Image Classification and Retrieval
References
[1] LI W, XIE Q, AO J, et al. Systematic review: a scientometric analysis of the status, trends and challenges in the application of digital technology to cultural heritage conservation (2019–2024). npj Heritage Science, 2025, 13: 90. DOI: 10.1038/s40494-025-01636-8.
[2] QUAN H, LI Y, LIU D, et al. Protection of Guizhou Miao batik culture based on knowledge graph and deep learning. Heritage Science, 2024, 12: 202. DOI: 10.1186/s40494-024-01317-y.
[3] WANG W J, LIU Y, XIAO L, et al. Digitalization of ancient Shu brocade patterns based on an improved generative adversarial network and vector drawing technology. Journal of Silk, 2023, 60(11): 18-27.
[4] SMEULDERS A W M, WORRING M, SANTINI S, et al. Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(12): 1349-1380. DOI: 10.1109/34.895972.
[5] SUN K K, HUANG J W, YUAN Y Y, et al. Classification and recognition of the Nantong blue calico pattern based on deep learning. Journal of Engineered Fibers and Fabrics, 2024, 19: 15589250241270618. DOI: 10.1177/15589250241270618.
[6] VARSHNEY S, SINGH S, LAKSHMI C V, et al. Content-based image retrieval of Indian traditional textile motifs using deep feature fusion. Scientific Reports, 2024, 14: 10035. DOI: 10.1038/s41598-024-56465-9.
[7] LIU Z, LIN Y, CAO Y, et al. Swin Transformer: Hierarchical vision transformer using shifted windows//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 10012-10022. DOI: 10.1109/ICCV48922.2021.00986.
[8] CODD E F. A relational model of data for large shared data banks. Communications of the ACM, 1970, 13(6): 377-387. DOI: 10.1145/362384.362685.
[9] WILKINSON M D, DUMONTIER M, AALBERSBERG I J, et al. The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data, 2016, 3: 160018. DOI: 10.1038/sdata201618.
[10]YEE K P, SWEARINGEN K, LI K, et al. Faceted metadata for image search and browsing//Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. New York: ACM, 2003: 401-408. DOI: 10.1145/642611. 642681.