Geometrically Invariant Image Blind Watermarking Based on Speeded-Up Robust Features and DCT Transform

In this paper, we propose a novel robust image blind watermarking scheme based on Speeded-Up Robust Features (SURF) region and Discrete Cosine Transform (DCT). As SURF features are invariant to rotation and scaling, we employ SURF to extract feature points. Then circular patches are generated using the feature points. The watermark is embedding each circular patch based on DCT transform which can resist signal processing attacks. Multiple patches have been embedded watermark for resisting locally cropping attacks. Experimental results show that the proposed scheme is robust to both geometric attacks and signal processing attacks.

[1]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[2]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[3]  Heung-Kyu Lee,et al.  Robust image watermarking using local invariant features , 2006 .

[4]  Axel Pinz,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[5]  Thierry Pun,et al.  Rotation, scale and translation invariant spread spectrum digital image watermarking , 1998, Signal Process..

[6]  Wen-Chuan Wu,et al.  A DCT-based robust image watermarking using local moment , 2011, The 3rd International Conference on Data Mining and Intelligent Information Technology Applications.

[7]  Benoit M. Macq,et al.  Geometrically invariant watermarking using feature points , 2002, IEEE Trans. Image Process..

[8]  Ingemar J. Cox,et al.  The First 50 Years of Electronic Watermarking , 2002, EURASIP J. Adv. Signal Process..

[9]  Nikolas P. Galatsanos,et al.  Digital watermarking robust to geometric distortions , 2005, IEEE Transactions on Image Processing.