DIGITAL IMAGE WATERMARKING BASED ON BAYESIAN COMPRESSIVE SENSING

A digital watermarking method based on Bayesian compressive sensing (BCS) is proposed in this paper. The watermark is embedded in the wavelet domain using the measurement matrix, and the watermarking extraction is accomplished using the Bayesian compressive sensing. Comparisons of watermarking extraction and anti-attack are given using orthogonal matching pursuit (OMP), basis pursuit (BP), and BCS. The experiments show that, compared with OMP and BP, the proposed watermarking method based on the BCS can provide improved performance, in terms of PSNR and NC, without much computational time.