A Copyright Protection Scheme for Gray-Level Images Using Human Fingerprint

This paper proposes a copyright protection scheme using human fingerprint images as watermarks. The scheme includes the feature extraction of the fingerprint image and the generation of the share image used to retrieve the fingerprint image. If an unauthorized copy is found later, the origin of the copy can be determined by the retrieved fingerprint image. Fingerprint image enhancement technique is employed prior to feature extraction to obtain a more reliable estimation of feature locations. In addition, the paper employs correction to reform the quality of the fingerprint image. According to the experimental results, the acceptance rate is up to 99% under several severe conditions. The experimental results also show that the scheme can tolerate several image processing attacks on the host image.