Crawling, Indexing, and Similarity Searching Images on the Web

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.

Authors	BATKO Michal FALCHI Fabrizio LUCCHESE Claudio NOVÁK David PEREGO Raffaele RABITTI Fausto SEDMIDUBSKÝ Jan ZEZULA Pavel
Year of publication	2008
Type	Article in Proceedings
Conference	Proceedings of the Sixteenth Italian Symposium on Advanced Database Systems
MU Faculty or unit	Faculty of Informatics
Citation
Field	Informatics
Keywords	similarity search; content-based image retrieval; metric space; MPEG-7 descriptors; peer-to-peer search network
Description	In this paper, we report on our experience in building an experimental similarity search system on a test collection of more than 50 million images, to show the possibility to scale Content-based Image Retrieval (CBIR) systems towards the Web size. First, we had to tackle the non-trivial process of image crawling and descriptive feature extraction, performed by using the European EGEE computer GRID, building a test collection, the first of such scale, that will be opened to the research community for experiments and comparisons. Then, we had to develop indexing and searching mechanisms which can scale up to these volumes and answer similarity queries in real-time. The results of our experiments are very encouraging for future applications.
Related projects:	Integrated approach to education of PhD students in the area of parallel and distributed systems Intelligent Models, Algorithms, Methods and Tools for the Semantic Web (realization) Complex similarity searching in very large data collections