A digital watermarking scheme for personal image authentication using eigenface

Authors:
Chien-Hsung Chen;Long-Wen Chang
Affiliations:
Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan;Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan
Venue:
PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part III
Year:
2004

Citing 8
Cited 1

Cryptography and network security (2nd ed.): principles and practice

Cryptography and network security (2nd ed.): principles and practice
Inside risks: the uses and abuses of biometrics

Communications of the ACM
Hiding a Face in a Fingerprint Image

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Copyright protection of images using robust digital signatures

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 04
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Resolving rightful ownerships with invisible watermarking techniques: limitations, attacks, and implications

IEEE Journal on Selected Areas in Communications
Secure spread spectrum watermarking for multimedia

IEEE Transactions on Image Processing
A buyer-seller watermarking protocol

IEEE Transactions on Image Processing

Tamper detection and self-recovery of biometric images using salient region-based authentication watermarking scheme

Computer Standards & Interfaces

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, face recognition has received a great of attention because digital camera can be widely available. It has many applications including security management in the airport and the IC card for e-commerce. In this paper, we introduce a watermark technique for image authentication with a personal face. We try to compute the eigenface of a personal image and encode the eigenface features with bar-code. The bar-coded feature values are then embedded into the image that is to be authenticated. Our simulation shows the similarity measures of the watermark extracted from the damaged image under various attack are vary high and indicate the proposed method is very feasible for real applications.