A search engine for historical manuscript images
Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Multilingual online access to digitised Arabic manuscripts by using metadata
International Journal of Metadata, Semantics and Ontologies
| Hi-index | 0.00 |
To date, only a small percentage of the earth's historical written records have been tapped into to contribute to our knowledge of our past. Our project aims at leveraging the work of the thousands of frequent or occasional visitors of the world's archives to accumulate and disseminate the raw transcriptions produced by the army of researchers who are digging into this treasure-trove of information from our antiquity. Since written records of our past are by definition finite, our system will put in place a mechanism that promises to capture - once and for all - the written records that our ancestors left behind. This paper describes an emergent system architecture that promises to eliminate redundancy by gradually yet systematically creating a cumulative, distributed, electronic repository of digital transcriptions of the written records form our past, that can be shared and searched without duplications and overlaps. Testing and evaluation of the system will begin in the summer of 2005.