A new digital image watermarking approach based on DWT-SVD and CPPN-NEAT

Digital watermarking has been proposed as a way to claim ownership. In this paper, a new approach in digital image watermarking based on discrete wavelet transform (DWT) and singular value decomposition (SVD) is presented. We use compositional pattern producing networks (CPPNs) to make a very compact representation of watermark. Using Neuro Evolution of Augmenting Topologies (NEAT) will evolve the CPPN structure to produce a suitable watermark image. In the embedding phase, at first we perform decomposing of the host image with 2D-DWT transform at 5-level, then the SVD is applied to LH3-LH5 sub-bands of transformed image, and embed the watermark by modifying the singular values. In watermark extraction phase, the embedded coefficients of CPPN neat are extracted from the watermarked image. Then the watermark image is rendered by CPPN. The experiments indicate that the watermark is robust against the different attacks, such as average filter, Jpeg compression and etc.