A robust content-based watermarking scheme

Content-based watermarking techniques have been widely developed to resist geometrical attacks. In the content-based watermarking scheme, invariant regions detected by an affine-invariant detector are exploited for watermark embedding. However, many image manipulations, including watermark embedding, will bring noise to the host image. It results in creating new interest points, removing existing points and changing the shape of invariant regions. Consequently, invariant region detection obtains different results between the embedder and the detector of a watermarking scheme. Thus, the watermark fails to be detected because of the loss of synchronization. In this paper, we present a novel content-based watermarking scheme providing robustness to such manipulations. First, the scale and affine invariant regions are extracted on the de-noised image. A new measure is proposed to select non-overlapping invariant regions out of the available invariant regions for watermark embedding. The watermark is embedded surrounding the selected invariant region. The experimental results show that the proposed scheme is robust to various image processing, including geometric attacks, JPEG compression and filtering.