Unsupervised clustering of pulsed infrared thermography for automated assessment of a Qing Dynasty brass mirror
Bibliographic Data
| ID | 24229786 |
|---|---|
| Authors | Haifeng Tang (0000-0002-9019-0260), Xue Yang (0000-0001-9747-6467), Zhenglin Xie (0000-0002-8625-0718), Guan Wang (0000-0001-8202-9939), Pan Xiao (0000-0001-5129-9346), Qi Liu (0000-0001-6077-361X) |
| Year | 2026 |
| Volume | 82 |
| Pages | 265-273 |
| Publication date | 2026-11-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Journal of Cultural Heritage (JOURNAL) |
| Journal identifiers | ISSN: 1296-2074 • E-ISSN: 1778-3674 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.culher.2026.09.019 |
| OpenAlex | W7221363713 |
| Language | EN |
| References cited | 42 |
Non-destructive assessment of complex multi-layered structures in cultural heritage artifacts, such as Qing Dynasty lacquer-coated brass mirrors, is critical for conservation and technical study. Pulsed thermography (PT), an active infrared thermographic technique, provides pixel-wise temporal thermal responses sensitive to subsurface variations, but machine-learning-based interpretation is often limited by the scarcity of annotated data. To address this challenge, a fully unsupervised framework combining Thermographic Signal Reconstruction (TSR), a Deep Autoencoder (DAE), and a Gaussian Mixture Model (GMM) is proposed to cluster thermal responses and extract thermally distinct subsurface features without prior labeling. The method was validated on a custom-designed test sample and successfully applied to a Qing Dynasty lacquered brass mirror, revealing spatially distinct thermal-response patterns associated with the lacquer-adhesive coating system. This label-free approach provides a practical tool for non-destructive evaluation of cultural heritage objects, offers new insights into historical craftsmanship, and is extendable to other metal-coating systems, supporting preservation strategies and informed conservation decision-making.
cultural heritage preservation · deep autoencoder · Gaussian mixture model · non-destructive assessment · pulsed infrared thermography · subsurface features · thermographic signal reconstruction · unsupervised clustering · Cultural Heritage Materials Analysis · Infrared Thermography in Medicine · Thermography and Photoacoustic Techniques
Faster R-CNN
Model-Based Clustering, Discriminant Analysis, and Density Estimation
Least squares quantization in PCM
Reducing the Dimensionality of Data with Neural Networks
Painting Bronze in Early China
Attention-enhanced U-Net for automatic crack detection in ancient murals using optical pulsed thermography
Defect detection
Applications of infrared thermography for the investigation of historic structures
| Highly cited | No |
|---|