Fingerprint information maximization for content identification

@article{Naini2014FingerprintIM,
  title={Fingerprint information maximization for content identification},
  author={Rohit Naini and Pierre Moulin},
  journal={2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2014},
  pages={3809-3813}
}
This paper presents a novel design of content fingerprints based on maximization of the mutual information across the distortion channel. We use the information bottleneck method to optimize the filters and quantizers that generate these fingerprints. A greedy optimization scheme is used to select filters from a dictionary and allocate fingerprint bits. We test the performance of this method for audio fingerprinting and show substantial improvements over existing learning based fingerprints. 

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 15 references

Pairwise Boosted Audio Fingerprint

IEEE Transactions on Information Forensics and Security • 2009
View 7 Excerpts
Highly Influenced

Model-based decoding metrics for content identification

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2012
View 1 Excerpt

Real Adaboost for content identification

2012 IEEE Statistical Signal Processing Workshop (SSP) • 2012
View 1 Excerpt

Multimedia Protection using Content and Embedded Fingerprints

A. L. Varna
Ph.D. thesis, University of Maryland, • 2011
View 2 Excerpts

Kernel Density Estimation via Diffusion

I. Z., BOTEV, +3 authors Ben Kröse
2010
View 1 Excerpt

Statistical modeling and analysis of content identification

2010 Information Theory and Applications Workshop (ITA) • 2010
View 2 Excerpts

Robust Video Fingerprinting Based on Symmetric Pairwise Boosting

IEEE Transactions on Circuits and Systems for Video Technology • 2009
View 1 Excerpt

Learning to hash: forgiving hash functions and applications

Data Mining and Knowledge Discovery • 2008
View 1 Excerpt

Similar Papers

Loading similar papers…