Robust image watermarking based on Riesz transformation and IT2FLS

Abstract

Conventional digital image watermarking techniques are often vulnerable to image processing and geometric distortions such as Rotation, Scaling, and Translation (RST). These distortions desynchronize the watermark information embedded in an image and thus disable watermark detection. To address this problem, we propose robust watermarking technique using the Riesz Transformation (RT). In the proposed method, watermark is embedded using simple addition and quantization based watermarking technique. In addition, Interval Type-2 Fuzzy Logic System (IT2FLS) is utilized for data fusion and building a model for spatial masking in the Riesz wavelet domain. Cross correlation method based on Neyman–Pearson and normalized correlation (NC) method are deployed for watermark detection and extraction respectively. Experimental results confirmed that the RT based technique is robust against image processing and geometric attack compared to previous techniques and has a good balance between robustness and imperceptibility under the checkmark tool.