Proceedings chapter

Privacy-Preserving Multimodal Person and Object Identification

Presented at Oxford (UK), Sep 22-23
Publication date2008

In this paper we investigate multimodal biometric person and object identification. We model this process of multimodal identification as multimodal multiple hypothesis testing with independent modalities. We analyze theoretical performance limits that can be attained in such a multimodal protocol in terms of exponents of average error probability. Furthermore, we address a privacy related issues in this paper. In particular, we consider performance/privacy trade-off due to the indirect multimodal identification performed in a secret subspace and approximate the obtained performance limits using properties of random projections. Finally, a set of experiments exemplifies our findings.

  • Watermarking
  • Multimodal identification
  • random projections, Chernoff dis- Tance
  • probability of error
Citation (ISO format)
KOVAL, Oleksiy, VOLOSHYNOVSKYY, Svyatoslav, PUN, Thierry. Privacy-Preserving Multimodal Person and Object Identification. In: Proceedings of the 10th ACM Workshop on Multimedia & Security. Oxford (UK). [s.l.] : ACM, 2008. p. 177–184. doi: 10.1145/1411328.1411359
Main files (1)
Proceedings chapter (Accepted version)

Technical informations

Creation03/06/2015 5:12:07 PM
First validation03/06/2015 5:12:07 PM
Update time03/14/2023 10:58:34 PM
Status update03/14/2023 10:58:34 PM
Last indexation08/29/2023 3:09:03 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack