Pruning SIFT for Scalable Near-duplicate Image Matching

Foo, J.J. and Sinha, R.

The detection of image versions from large image col- lections is a formidable task as two images are rarely identical. Geometric variations such as cropping, rotation, and slight photometric alteration are unsuitable for content-based retrieval techniques, whereas digital watermarking techniques have limited application for practical retrieval. Recently, the application of Scale Invariant Feature Transform (SIFT) interest points to this domain have shown high effectiveness, but scalability remains a problem due to the large number of features generated for each image. In this work, we show that for this application domain, the SIFT interest points can be dramatically pruned to effect large reductions in both memory requirements and query run-time, with almost negligible loss in ef- fectiveness. We demonstrate that, unlike using the original SIFT features, the pruned features scales bet- ter for collections containing hundreds of thousands of images

Cite as: Foo, J.J. and Sinha, R. (2007). Pruning SIFT for Scalable Near-duplicate Image Matching. In Proc. Eighteenth Australasian Database Conference (ADC 2007), Ballarat, Australia. CRPIT, 63. Bailey, J. and Fekete, A., Eds. ACS. 63-71.

(from crpit.com) (local if available)