Machine learning based blind color image watermarking scheme for copyright protection

Abstract This work presents a blind and robust scheme using YCbCr color space, IWT (integer wavelet transform) and DCT (discrete cosine transform) for color image watermarking. During watermark insertion, Y channel is divided into blocks and Mersenne Twister random number generator is used to select the blocks for embedding. This randomized selection of blocks required a secret key, thus improving the security of the scheme. To reduce the computational complexity, the artificial neural network architecture is developed for watermark embedding. To check the robustness, several signal processing attacks such as JPEG compression, filtering attacks, noise attacks, cropping, resizing and other common attacks are applied on the watermarked images. The proposed work is tested on different images to verify the similarity in watermarking results. The scheme provides similar results (having little variation) for different test images. Experimental results demonstrate the superior performance in terms of imperceptibility and robustness. Further, the ANN framework provides faster embedding with approximately similar parametric results. The performance comparison with existing schemes demonstrates better performance for different attacks. The proposed work can be used in robust applications (i.e. copyright protection) for efficient results and less computational time.