Automatic Analysis of Mexican Codex Collections
This is a joint project between Idiap Research Institute and the National Institute of Anth ropology and History (INAH, Instituto Nacional de Antropología e Historia) of Mexico.
The aim of the project is to advance the state-of-the-art on robust representation, categorization and matching of visual features, (appearance and shape) in complex image collections by developing probabilistic methods.
Although the developed methods will be general, robust approaches for these fundamental problems will eventually be integrated in tools to support and improve the job of archaeologists and other people who frequently manage these kind of image data bases.
The analysis will be done over a collection of Original Mexican Codices of Maya culture provided by the (INAH). This collection, one of UNESCO’s Treasures of the World, features a considerable number of ancient pictorial documents and constitutes an invaluable source of information about the history, language, beliefs, and social structure of the indigenous cultures that inhabited Mexico before and soon after the Conquest of America.
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.
Partners
National Institute of Anth ropology and History (INAH, Instituto Nacional de Antropología e Historia) of Mexico
