SIFT based robust image watermarking resistant to resolution scaling

Abstract

In this paper, a novel image watermarking scheme is proposed which is robust to resolution scaling. In the proposed method, SIFT (Scale Invariant Feature Transform) features are used which are invariant to rotation, translation and scaling. Most of the existing watermarking algorithms that uses SIFT features, fail to retain the watermark when the image is heavily scaled down. In the proposed scheme, a context coherent object or patch is inserted in the image such that it generates strong SIFT features. These newly generated SIFT features themselves work as a watermark. Since the SIFT features are invariant to scaling, these features can be extracted from any image resolution with high probability. The experimental results support the contention that the proposed method is considerably robust against resolution scaling.