Indexing Tamper Resistant Features for Image Copy Detection

In this paper we present the image copy detection service we have built. We call this service RIME, for Replicated IMage dEtector. Given an image registered by its creator or distributor, RIME checks if near-replicas of the image (i.e., copies of the image that may have gone through alterations) exist on the Internet and returns a list of suspect URLs. The core technologies that the RIME project develops are effective image characterization for copy detection, and efficient image indexing for finding images with similar characteristics.

[1]  Jing Huang,et al.  Combining supervised learning with color correlograms for content-based image retrieval , 1997, MULTIMEDIA '97.

[2]  Shih-Fu Chang,et al.  Tools and techniques for color image retrieval , 1996, Electronic Imaging.

[3]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[4]  Edward Y. Chang,et al.  Searching near-replicas of images via clustering , 1999, Optics East.

[5]  Tat-Seng Chua,et al.  An integrated color-spatial approach to content-based image retrieval , 1995, MULTIMEDIA '95.

[6]  Edward Y. Chang,et al.  Clindex: Clustering for Similarity Queries in High-Dimensional Spaces. , 1999 .

[7]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Edward Y. Chang,et al.  RIME: a replicated image detector for the World Wide Web , 1998, Other Conferences.

[9]  Ramin Zabih,et al.  Comparing images using color coherence vectors , 1997, MULTIMEDIA '96.

[10]  Ramin Zabih,et al.  Histogram refinement for content-based image retrieval , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[11]  Hector Garcia-Molina,et al.  Safeguarding and charging for information on the Internet , 1998, Proceedings 14th International Conference on Data Engineering.