Searching near-replicas of images via clustering

Edward Y. Chang, Chen Li, James Ze Wang, Peter Mork, Gio Wiederhold

Research output: Contribution to journalConference article

28 Scopus citations

Abstract

Internet piracy has been one of the major concerns for Web publishing. In this study we present a system, RIME, that we have prototyped for detecting unauthorized image copying on the World-Wide Web. To speed up the copy detection, RIME uses a new clustering/hashing approach that first clusters similar images on adjacent disk cylinders and then builds indexes to access the clusters made in this way. Searching for the replicas of all image often takes just one IO to look up the location of the cluster containing similar objects and one sequential file IO to read in this cluster. Our experimental results show that RIME can detect image copies both more efficiently and effectively than the traditional content-based image retrieval systems that use tree-like structures to index images. In addition, RIME copes well with image format conversion, resampling, requantization and geometric transformations.

Original languageEnglish (US)
Pages (from-to)281-292
Number of pages12
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume3846
StatePublished - Dec 1 1999
EventProceedings of the 1999 Multimedia Storage and Archiving Systems IV - Boston, MA, USA
Duration: Sep 20 1999Sep 22 1999

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Searching near-replicas of images via clustering'. Together they form a unique fingerprint.

  • Cite this