We are delighted to announce a new publication by our Laboratory in the international scientific journal Heritage:
E., Nerantzis, L., Malletzidou, E., Kyratzopoulou, N., Tsirliganis, C.N., Kazakis, N.A., 2025. From Contemporary Datasets to Cultural Heritage Performance: Explainability and Energy Profiling of Visual Models Towards Textile Identification. Heritage 8(11), 447. https://doi.org/10.3390/heritage8110447
The publication presents results from the research project:
“FiberScope – Towards the Automated Identification of Textile Fibres Using Microscopy and Machine Learning”,
funded by the “ARCHIMEDES: Research in Artificial Intelligence, Data Science and Algorithms” Unit (MIS 5154714), under the “Support for Basic and Applied Research” action of the “Greece 2.0” programme.
The study focuses on the development and evaluation of computer-vision models for textile-fibre identification, with particular emphasis on model explainability and energy efficiency. The results contribute to improving the reliability and sustainability of artificial-intelligence technologies in cultural heritage applications.
The publication highlights the contribution of the Laboratory of Archaeometry and Physicochemical Measurements to integrating machine learning with archaeometry and the analysis of cultural heritage materials.