CODICES is a joint project between Idiap Research Institute and Mexico's National Institute of Anthropology and History (INAH), funded by the Swiss National Science Foundation (SNSF).
The aim of the project is to design and evaluate probabilistic methods for robust representation, categorization, and matching of visual patterns in complex images of cultural and historical collections.
The developed methods are intended to be general, and will be integrated in tools to facilitate the job of archaeologists and other scholars who frequently make use of this kind of image collections.
The analysis is done over a photographic collection provided by INAH, which contains thousands of inscriptions from the Maya culture. This collection constitutes an invaluable source of information about the history, language, beliefs, and social structure of this ancient culture.
Overall, this project addresses the relevant problem of analyzing digital imagery of unique cultural heritage materials, through the development of new and principled analysis methods of wider applicability, integrating computer vision, information retrieval, and machine learning techniques.