A dimensionality reduction-based approach for secured color image watermarking

Recently, digital images are widely used in several applications through advanced wearable devices and networks. Despite several benefits of digital images, such as easy distribution, storage, and reproduction, it is difficult to prevent the issue of identity theft, privacy leakage, and ownership conflicts. To solve the above issues, dimensionality reduction-based robust watermarking for color images, supported with suitable encryption, is presented in this article. In this method, principal component analysis (PCA)-based dimensionality reduction is applied to the color carrier image to produce three principal components. The third component with minimum energy is then concealed with a mark image using non-sub-sampled shearlet transform (NSST)-singular value decomposition (SVD)-based watermarking to resolve the ownership issues, if any. In addition, encryption of marked image is done to provide better security and authenticity. The final encrypted image is then stored in a cloud environment for better accessibility. Finally, an experimental and comparative evaluation of the proposed framework justifies its versatility, robustness, and imperceptibility with the best improvement of 47.49 %.