Optimum detection of multiplicative-multibit watermarking for fingerprint images

Zebbiche, Khalil, Khelifi, Fouad and Bouridane, Ahmed (2007) Optimum detection of multiplicative-multibit watermarking for fingerprint images. In: Advances in Biometrics. Lecture Notes in Computer Science, 4642 . Springer, London, pp. 732-741. ISBN 978-3540745488

Full text not available from this repository. (Request a copy)

Abstract

Watermarking is an attractive technique which can be used to ensure the security and the integrity of fingerprint images. This paper addresses the problem of optimum detection of multibit, multiplicative watermarks embedded within Generalized Gaussian distribution features in Discrete Wavelet Transform of fingerprint images. The structure of the proposed detector has been derived using the maximum-likelihood approach and the Neyman-Pearson criterion. The parameters of the Generalized Gaussian distribution are directly estimated from the watermarked image, which makes the detector more suitable for real applications. The performance of the detector is tested by taking into account the different quality of fingerprint images and different attacks. The results obtained are very attractive and the watermark can be detected with low detection error. Also, the results reveal that the proposed detector is more suitable for fingerprint images with good visual quality.

Item Type:	Book Section
Additional Information:	Proceedings of the ICB 2007: International Conference, Seoul, Korea, August 27-29, 2007.
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Sarah Howells
Date Deposited:	21 Nov 2012 16:32
Last Modified:	12 Oct 2019 22:29
URI:	http://nrl.northumbria.ac.uk/id/eprint/10352

Downloads