Abstract | ||
---|---|---|
This paper considers generating binary feature vectors from biometric face data such that their privacy can be protected using recently introduced helper data systems. We explain how the binary feature vectors can be derived and investigate their statistical properties. Experimental results for a subset of the FERET and Caltech databases show that their is only a slight degradation in classification results when using the binary rather than the real-valued feature vectors. Finally, the scheme to extract the binary vectors is combined with a helper data scheme leading to re-newable and privacy preserving facial templates with acceptable classification results provided that the within-class variation is not too large. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/AUTOID.2005.24 | AutoID |
Keywords | Field | DocType |
helper data system,binary vector,face recognition,real-valued feature vector,helper data scheme,biometric face data,caltech databases,acceptable classification result,binary feature vector,classification result,privacy preserving binary templates,image classification,data privacy,statistical analysis,feature vector,feature extraction | Data mining,Facial recognition system,Feature vector,Pattern recognition,Data system,Computer science,Feature extraction,Artificial intelligence,Biometrics,Information privacy,Contextual image classification,Binary number | Conference |
ISBN | Citations | PageRank |
0-7695-2475-3 | 69 | 2.70 |
References | Authors | |
6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tom A. M. Kevenaar | 1 | 344 | 21.90 |
G. J. Schrijen | 2 | 69 | 2.70 |
M. van der Veen | 3 | 115 | 4.77 |
A. H. M. Akkermans | 4 | 158 | 11.48 |
Fei Zuo | 5 | 90 | 4.83 |