Fuzzy-ART Based Geometrically Invariant Robust Watermarking Scheme

This paper describes a novel transform domain oblivious image watermarking method that combines FuzzyART clustering and image normalization to design a watermarking system that is robust to any type of attacks like geometric attacks, jpeg compression, noise attacks and other image processing attacks. The use of Fuzzy ART clustering as a pre-processing step helps in the accurate selection of locations for watermark insertion so that the watermarked image is robust as well as perceptually invisible. The watermark is embedded adaptively using Just Noticeable Distortion (JND) mask that ensures the required quality for the watermarked image. The loss of synchronization in case of geometric attacks is corrected using image normalization technique that makes the watermark detectable even in the case of geometric attacks. Replicated copies of the binary watermark image are used to create a composite watermark that is scrambled using Arnold Transform which gives better reliability in extraction. Normalized Correlation (NC) is used as the verification metric.