Title: A robust watermarking technique for biometric image authentication

Authors: Mohamed Radouane; Nadia Idrissi Zouggari

Addresses: SPM Research Team, ENSIAS, Mohammed V University in Rabat, Morocco ' LCS Laboratory FSR, Mohammed V University in Rabat, Rabat, Morocco

Abstract: Biometric authentication data is becoming a crucial challenge to ensure copyright protection of digital images. A person's biometric data is very sensitive; if exposed, it can pose a threat to a person's identity and system security. Due to advances in watermarking, the most research is aimed at improving robustness to prevent attacks of biometric image. In this paper, we have proposed an invisible watermarking scheme for biometric image authentication using Gabor filter, Contourlet transform, discrete wavelet transform (DWT) and singular value decomposition (SVD). Features are extracted from biometric image and an iris watermark is embedded. The proposed method was tested on CASIA-v5 and CASIA-Palmprint-v1 datasets. The evaluation performance is done by different measuring metrics. The proposed approach is compared with different methods in the literature. It is found that the watermarked images are robust over different attacks. Results show that the proposed method provides protection to biometric images and gives better results in terms of PSNR and NC.

Keywords: copyright protection; authentication; Gabor filter; Contourlet transform; watermarking; discrete wavelet transform; DWT; singular value decomposition; SVD; peak signal to noise ratio; PSNR; bit error rate; BER.

DOI: 10.1504/IJBM.2023.133165

International Journal of Biometrics, 2023 Vol.15 No.5, pp.587 - 605

Received: 16 Dec 2021
Accepted: 06 Jul 2022
Published online: 01 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article