Secure data hiding in wavelet compressed fingerprint images
MULTIMEDIA '00 Proceedings of the 2000 ACM workshops on Multimedia
Secure hybrid robust watermarking resistant against tampering and copy attack
Signal Processing - Special section: Security of data hiding technologies
IEEE Transactions on Pattern Analysis and Machine Intelligence
Enhancing security and privacy in biometrics-based authentication systems
IBM Systems Journal - End-to-end security
A watermarking-based image ownership and tampering authentication scheme
Pattern Recognition Letters
Face Description with Local Binary Patterns: Application to Face Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A majority-voting based watermarking scheme for color image tamper detection and recovery
Computer Standards & Interfaces
Data hiding based on compressed VQ indices of images
Computer Standards & Interfaces
A digital watermarking scheme for personal image authentication using eigenface
PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part III
A wavelet-based fragile watermarking scheme for secure image authentication
IWDW'06 Proceedings of the 5th international conference on Digital Watermarking
Fragile Watermarking Based on Encoding of the Zeroes of the -Transform
IEEE Transactions on Information Forensics and Security
Counterfeiting attacks on oblivious block-wise independent invisible watermarking schemes
IEEE Transactions on Image Processing
Secret and public key image watermarking schemes for image authentication and ownership verification
IEEE Transactions on Image Processing
Protecting biometric templates with image watermarking techniques
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Bayesian Segmentation Based Local Geometrically Invariant Image Watermarking
Fundamenta Informaticae
Hi-index | 0.00 |
Biometric images can be split into regions of salient (ROI) and regions of background (ROB) based on salient region detection. During the process of watermark embedding, salient regions which contain rich-information are less affected by the watermark, therefore can be embedded into more watermarks, and regions of background (ROB) are susceptible to the effect of watermarks, so that they should be embedded lighter or even none in order to preserve the recognition quality of biometric images. In this paper, a novel scheme for tamper detection and self-recovery of biometric images using salient region-based authentication watermarking is proposed. Firstly, we propose a novel multi-level authentication watermarking scheme, which is used to verify the integrity of biometric images. Secondly, biometric data of these biometric images which is used as information watermarks is embedded into themselves. As a result, verification systems can recover the damaged data of original biometric images with hidden information based on tampering detection result. Experimental results and theoretic analysis show that our proposed scheme can detect tampered regions, and recover biometric data while keeping the recognition quality.