Rotation Invariant Localization of Duplicated Image Regions Based on Zernike Moments

TitleRotation Invariant Localization of Duplicated Image Regions Based on Zernike Moments
Publication TypeJournal Article
Year of Publication2013
AuthorsRyu, S-J., Kirchner M., Lee M-J., & Lee H-K.
Published inIEEE Transactions on Information Forensics and Security
Volume8
Issue8
Page(s)1355-1370
Other Numbers3466
Abstract

This paper proposes a forensic technique to localize duplicated image regions based on Zernike moments of small image blocks.We exploit rotation invariance properties to reliably unveil duplicated regions after arbitrary rotations. We devise a novel block matching procedure based on locality sensitive hashing and reduce false positives by examining the moments’ phase. A massive experimental test setup benchmarks our algorithm against state-of-the-art methods under various perspectives, examining both pixel-level localization and image-level detection performance. By taking signal characteristics into account and distinguishing between "textured" and "smooth" duplicated regions, we find that the proposed method outperforms prior art in particular when duplicated regions are smooth. Experiments indicate high robustness against JPEG compression, blurring, additive white Gaussian noise, and moderate scaling.Index Terms—Copy-move detection, duplicated region localization, locality sensitive hashing, Zernike moments.

URLhttps://www.icsi.berkeley.edu/pubs/vision/ICSI_rotationinvariantlocalization13.pdf
Bibliographic Notes

IEEE Transactions on Information Forensics and Security, Vol. 8, No. 8, pp. 1355-1370

Abbreviated Authors

S.-J. Ryu, M. Kirchner, M.-J. Lee, and H.-K. Lee

ICSI Research Group

Vision

ICSI Publication Type

Article in journal or magazine