Robust perceptual image hashing using feature points

Vishal Monga, Brian L. Evans

Research output: Chapter in Book/Report/Conference proceedingConference contribution

66 Scopus citations

Abstract

Perceptual image hashing maps an image to a fixed length binary string based on the image's appearance to the human eye, and has applications in image indexing, authentication, and watermarking. In this paper, we present a general framework for perceptual image hashing using feature points. The feature points should be largely invariant under perceptually insignificant distortions. To satisfy this, we propose an iterative feature detector to extract significant geometry preserving feature points. We apply probabilistic quantization on the derived features to further enhance perceptual robustness. The proposed hash algorithm withstands standard benchmark (e.g. Stirmark) attacks including compression, geometric distortions of scaling and small angle rotation, and common signal processing operations. Content changing (malicious) manipulations of image data are also accurately detected.

Original languageEnglish (US)
Title of host publication2004 International Conference on Image Processing, ICIP 2004
Pages677-680
Number of pages4
DOIs
StatePublished - Dec 1 2004
Event2004 International Conference on Image Processing, ICIP 2004 - , Singapore
Duration: Oct 24 2004Oct 27 2004

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume1
ISSN (Print)1522-4880

Other

Other2004 International Conference on Image Processing, ICIP 2004
CountrySingapore
Period10/24/0410/27/04

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'Robust perceptual image hashing using feature points'. Together they form a unique fingerprint.

Cite this