Blind Color Image Watermarking using Deep Artificial Neural Network using statistical features

Abstract With increasing digital content over the internet it is very important to secure the digital contents in such a way that the identity and integrity of data is preserved in some way. The healthcare data is also a digital content which is important and this paper presents a methodology for copyright protection and authorship. In order to achieve a balance between imperceptibility and robustness a robust watermarking scheme is proposed using deep artificial neural network (DNN) and lifting wavelet transform. YIQ color model is utilized for image watermarking and statistical features have been obtained for creating training and testing set. Here watermark extraction is done as a binary classification technique and PCA is utilized for reducing the feature set. Ten standard images have been used for image watermarking and for threshold value 0.3 it shows the average imperceptibility of 51.08 dB and shows good robustness under various image attacks.