Robust biometric image watermarking for fingerprint and face template protection

This paper presents a combined DWT and LSB based biometric watermarking algorithm that securely embeds a face template in a fingerprint image. The proposed algorithm is robust to geometric and frequency attacks and protects the integrity of both the face template and the fingerprint image. Experimental results performed on a database of 750 face and 750 fingerprint images show that the algorithm has the advantages of both the existing DWT and LSB based algorithms. A multimodal biometric algorithm is used as a metric to evaluate the combined performance of both face and fingerprint recognition.

[1]  Anil K. Jain,et al.  On-line fingerprint verification , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[2]  Deepa Kundur,et al.  Digital watermarking using multiresolution wavelet decomposition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[3]  Markus G. Kuhn,et al.  Information hiding-a survey , 1999, Proc. IEEE.

[4]  Anil K. Jain,et al.  Hiding Biometric Data , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Arun Ross,et al.  Information fusion in biometrics , 2003, Pattern Recognit. Lett..

[6]  Richa Singh,et al.  Improving biometric recognition accuracy and robustness using DWT and SVM watermarking , 2005, IEICE Electron. Express.

[7]  Mayank Vatsa,et al.  Textural feature based face recognition for single training images , 2005 .