Creating a dataset of digital images of Byzantine frescoes for analysis and classification using machine learning techniques
Abstract
The methodology for creating a database of fresco images, mainly of the Macedonian School (13th-14th century), is presented here. This base will be used later for digital image processing for classification using machine learning. For this purpose, modern digital data analysis tools in Python were used. The collection of appropriate material, the digitization of images, the input of information and the categories examined are presented in detail, along with the tools used. One of the main problems of the research was that there were no open digital libraries to cover with images of the specific period examined, so the material gathered comes from corporate sources such as books, studies and collectors. After analyzing the art historical information from Byzantine frescoes not only for their measurability and reliability, but also for availability, a python application that manages the data as an object-oriented relational graph is created. This is a first approach to such material that combines easy-to-use tools with historical knowledge and provides a ready-to-use and development base.
Article Details
- How to Cite
-
Vlisidi, A., & Moropoulou, A. (2024). Creating a dataset of digital images of Byzantine frescoes for analysis and classification using machine learning techniques . International Symposium on the Conservation of Monuments in the Mediterranean Basin, 177–182. https://doi.org/10.12681/monubasin.8183
- Section
- Part IV - Methodologies for Characterization and Damage Assessment
You are free to:
- Share — copy and redistribute the material in any medium or format
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- NonCommercial — You may not use the material for commercial purposes.
- NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
