Towards a Robust Feature-Based Watermarking Scheme

This paper presents a feature-based watermarking scheme which is robust to geometric and common image processing attacks. The improved Harris corner detector is used to find the robust feature points, which correspond to high corner responses and survive various attacks. The watermark is embedded in the Fourier frequency domain of the disk area centered at each feature point to ensure the resilience to the local attacks and common image processing. The image normalization method is adopted to determine the possible rotation for reducing synchronization errors between the embedded and extracted watermarks. The watermark detection decision is based on the number of matched disks in terms of the number of matched bits between the recovered and embedded watermarks in embedding blocks. Experimental results demonstrate that our scheme is more robust to geometric and common image processing attacks than the peer feature-point-based approaches.