Pruning SIFT for scalable near-duplicate image matching

This work shows 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 effectiveness.

Abstract

The detection of image versions from large image collections 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 effectiveness. We demonstrate that, unlike using the original SIFT features, the pruned features scales better for collections containing hundreds of thousands of images.