High-confidence near-duplicate image detection

  • Authors:

  • Wei Dong;Zhe Wang;Moses Charikar;Kai Li

  • Affiliations:

  • Independent Researcher, Ann Arbor MI;Princeton University, Princeton, NJ;Princeton University, Princeton, NJ;Princeton University, Princeton, NJ

  • Venue:
  • Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
  • Year:
  • 2012

  • Twitter's visual pulse

    Proceedings of the 3rd ACM conference on International conference on multimedia retrieval

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose two techniques for near-duplicate image detection at high confidence and large scale. First, we show that entropy-based filtering eliminates ambiguous SIFT features that cause most of the false positives, and enables claiming near-duplicity with a single match of the retained high-quality features. Second, we show that graph cut can be used for query expansion with a duplicity graph computed offline to substantially improve search quality. Evaluation with web images show that when combined with sketch embedding [6], our methods achieve false positive rate orders of magnitude lower than the standard visual word approach. We demonstrate the proposed techniques with a large-scale image search engine which, using indexing data structure offline computed with a Hadoop cluster, is capable of serving more than 50 million web images with a single commodity server.