Scalability of Local Image Descriptors: A Comparative Study

Herwig Lejsek (1) , Friðrik Heiðar Ásmundsson (1) , Björn Þór Jónsson (1) , Laurent Amsaleg (2)

1 School of Computer Science [Reykjavik]
2 TEXMEX - Multimedia content-based indexing

Computer vision researchers have recently proposed several local descriptor schemes. Due to lack of database support, however, these descriptors have only been evaluated using small image collections. Recently, we have developed the PVS-framework, which allows efficient querying of large local descriptor collections. In this paper, we use the PVS-framework to study the scalability of local image descriptors. We propose a new local descriptor scheme and compare it to three other well known schemes. Using a collection of almost thirty thousand images, we show that the new scheme gives the best results in almost all cases. We then give two stop rules to reduce query processing time and show that in many cases only a few query descriptors must be processed to find matching images. Finally, we test our descriptors on a collection of over three hundred thousand images, resulting in over 200 million local descriptors, and show that even at such a large scale the results are still of high quality, with no change in query processing time.

Domaines: Base de données [cs.DB]; Multimédia [cs.MM]; Traitement des images [eess.IV]

Herwig Lejsek, Friðrik Heiðar Ásmundsson, Björn Þór Jónsson, Laurent Amsaleg. Scalability of Local Image Descriptors: A Comparative Study. Proceedings of the 14th annual ACM international conference on Multimedia, Oct 2006, Santa Barbara, United States. ⟨10.1145/1180639.1180760⟩. ⟨inria-00175234⟩