BATKO, Michal, Fabrizio FALCHI, Claudio LUCCHESE, David NOVÁK, Raffaele PEREGO, Fausto RABITTI, Jan SEDMIDUBSKÝ and Pavel ZEZULA. Building a Web-scale Image Similarity Search System. Multimedia Tools and Applications. Springer Netherlands, 2010, vol. 47, No 3, p. 599-629. ISSN 1380-7501. |
Other formats:
BibTeX
LaTeX
RIS
@article{842607, author = {Batko, Michal and Falchi, Fabrizio and Lucchese, Claudio and Novák, David and Perego, Raffaele and Rabitti, Fausto and Sedmidubský, Jan and Zezula, Pavel}, article_number = {3}, keywords = {similarity search; content-based image retrieval; metric space; MPEG-7 descriptors; peer-to-peer search network}, language = {eng}, issn = {1380-7501}, journal = {Multimedia Tools and Applications}, title = {Building a Web-scale Image Similarity Search System}, url = {http://www.springerlink.com/content/u6112378t8k63382/}, volume = {47}, year = {2010} }
TY - JOUR ID - 842607 AU - Batko, Michal - Falchi, Fabrizio - Lucchese, Claudio - Novák, David - Perego, Raffaele - Rabitti, Fausto - Sedmidubský, Jan - Zezula, Pavel PY - 2010 TI - Building a Web-scale Image Similarity Search System JF - Multimedia Tools and Applications VL - 47 IS - 3 SP - 599-629 EP - 599-629 PB - Springer Netherlands SN - 13807501 KW - similarity search KW - content-based image retrieval KW - metric space KW - MPEG-7 descriptors KW - peer-to-peer search network UR - http://www.springerlink.com/content/u6112378t8k63382/ N2 - As the number of digital images is growing fast and Content-based Image Retrieval (CBIR) is gaining in popularity, CBIR systems should leap towards Web-scale datasets. 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. The first big challenge we have been facing was obtaining a collection of images of this scale with the corresponding descriptive features. We have tackled the non-trivial process of image crawling and extraction of several MPEG-7 descriptors. The result of this effort is a test collection, the first of such scale, opened to the research community for experiments and comparisons. The second challenge was to develop indexing and searching mechanisms able to scale to the target size and to answer similarity queries in real-time. We have achieved this goal by creating sophisticated centralized and distributed structures based purely on the metric space model of data. We have joined them together which has resulted in an extremely flexible and scalable solution. In this paper, we study in detail the performance of this technology and its evolvement as the data volume grows by three orders of magnitude. The results of the experiments are very encouraging and promising for future applications. ER -
BATKO, Michal, Fabrizio FALCHI, Claudio LUCCHESE, David NOVÁK, Raffaele PEREGO, Fausto RABITTI, Jan SEDMIDUBSKÝ and Pavel ZEZULA. Building a Web-scale Image Similarity Search System. \textit{Multimedia Tools and Applications}. Springer Netherlands, 2010, vol.~47, No~3, p.~599-629. ISSN~1380-7501.
|