Watermarking Algorithm Based on Kernel Fuzzy Clustering and Singular Value Decomposition in the Complex Wavelet Transform Domain

To further enhance the performance of existing watermarking scheme, watermarking algorithm based on kernel fuzzy clustering and singular value decomposition in the complex wavelet transform domain is proposed in this paper. Firstly, the host image is decomposed by complex wavelet transform. Then, the singular value of the low-frequency coefficients after image complex wavelet is selected as an embedded object, which makes the watermarked image with good hiding. Finally, image low-frequency background and high-frequency texture features, which are related to human visual masking, are used as fuzzy clustering feature vectors to determine the different embedding strength. Experimental results show the proposed scheme is not only invisible and robust against common image processing such as sharpening, noise adding, smoothing filtering, JPEG compression and contrast enhancement, but also robust against the geometric attacks such as distortion, shearing. Especially, it performs better than other image watermarking schemes based on spatial and wavelet domain.