Integrating deep learning and machine learning for ceramic artifact classification and market value prediction
This study proposes an intelligent framework for the automated classification and valuation of ceramic artifacts, integrating deep learning and machine learning techniques. An improved YOLOv11 model was constructed to identify key ceramic attributes such as decorative patterns, shapes, and craftsman...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media Deutschland GmbH
2025
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/120159/ http://psasir.upm.edu.my/id/eprint/120159/1/120159.pdf |
| _version_ | 1848868126656036864 |
|---|---|
| author | Hu, Yanfeng Wu, Siqi Ma, Zhuoran Cheng, Si |
| author_facet | Hu, Yanfeng Wu, Siqi Ma, Zhuoran Cheng, Si |
| author_sort | Hu, Yanfeng |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | This study proposes an intelligent framework for the automated classification and valuation of ceramic artifacts, integrating deep learning and machine learning techniques. An improved YOLOv11 model was constructed to identify key ceramic attributes such as decorative patterns, shapes, and craftsmanship styles. The model achieved a mean Average Precision (mAP@50) of 70.0% and a recall of 91.0%, demonstrating strong capability in detecting complex visual features. Based on the extracted visual attributes, a Random Forest classifier was employed to predict price categories using multi-source auction data, achieving a test accuracy of 99.52%. Feature importance analysis further revealed manufacturing techniques and shape as key predictors of market value. The integrated framework effectively combines visual feature extraction and market-informed valuation, providing a scalable solution for intelligent ceramic appraisal and digital heritage curation. This approach supports both expert and non-expert applications, laying a foundation for future development of intelligent cultural heritage management systems. |
| first_indexed | 2025-11-15T14:47:26Z |
| format | Article |
| id | upm-120159 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:47:26Z |
| publishDate | 2025 |
| publisher | Springer Science and Business Media Deutschland GmbH |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1201592025-09-24T02:31:02Z http://psasir.upm.edu.my/id/eprint/120159/ Integrating deep learning and machine learning for ceramic artifact classification and market value prediction Hu, Yanfeng Wu, Siqi Ma, Zhuoran Cheng, Si This study proposes an intelligent framework for the automated classification and valuation of ceramic artifacts, integrating deep learning and machine learning techniques. An improved YOLOv11 model was constructed to identify key ceramic attributes such as decorative patterns, shapes, and craftsmanship styles. The model achieved a mean Average Precision (mAP@50) of 70.0% and a recall of 91.0%, demonstrating strong capability in detecting complex visual features. Based on the extracted visual attributes, a Random Forest classifier was employed to predict price categories using multi-source auction data, achieving a test accuracy of 99.52%. Feature importance analysis further revealed manufacturing techniques and shape as key predictors of market value. The integrated framework effectively combines visual feature extraction and market-informed valuation, providing a scalable solution for intelligent ceramic appraisal and digital heritage curation. This approach supports both expert and non-expert applications, laying a foundation for future development of intelligent cultural heritage management systems. Springer Science and Business Media Deutschland GmbH 2025 Article PeerReviewed text en cc_by_nc_nd_4 http://psasir.upm.edu.my/id/eprint/120159/1/120159.pdf Hu, Yanfeng and Wu, Siqi and Ma, Zhuoran and Cheng, Si (2025) Integrating deep learning and machine learning for ceramic artifact classification and market value prediction. npj Heritage Science, 13 (1). art. no. 306. pp. 1-17. ISSN 3059-3220 https://www.nature.com/articles/s40494-025-01886-6?error=cookies_not_supported&code=885a38c7-8a7b-4228-bf04-2efc768fc906 10.1038/s40494-025-01886-6 |
| spellingShingle | Hu, Yanfeng Wu, Siqi Ma, Zhuoran Cheng, Si Integrating deep learning and machine learning for ceramic artifact classification and market value prediction |
| title | Integrating deep learning and machine learning for ceramic artifact classification and market value prediction |
| title_full | Integrating deep learning and machine learning for ceramic artifact classification and market value prediction |
| title_fullStr | Integrating deep learning and machine learning for ceramic artifact classification and market value prediction |
| title_full_unstemmed | Integrating deep learning and machine learning for ceramic artifact classification and market value prediction |
| title_short | Integrating deep learning and machine learning for ceramic artifact classification and market value prediction |
| title_sort | integrating deep learning and machine learning for ceramic artifact classification and market value prediction |
| url | http://psasir.upm.edu.my/id/eprint/120159/ http://psasir.upm.edu.my/id/eprint/120159/ http://psasir.upm.edu.my/id/eprint/120159/ http://psasir.upm.edu.my/id/eprint/120159/1/120159.pdf |