SVR-based oblivious watermarking scheme

Abstract

With the development of Internet, digital medias can be easily redistributed which renders copyright protection issues. A novel support vector regression (SVR) based oblivious watermarking scheme for color image is proposed in this paper. The watermark is embedded into the blue channel of color images by applying the good learning ability of SVR. Using the information of unmodified reference positions, the SVR can be trained well. Thanks to the good generalization ability of SVR, the watermark can be correctly extracted under several different attacks. Experimental results show that the proposed scheme have outperforming performance over Kutter's method against several different attacks including noise addition, shearing, luminance & contrast enhancement, distortion, etc. © Springer-Verlag Berlin Heidelberg 2005.