Desynchronization Attacks Resistant Watermarking for Remote Sensing Images Based on DWT‐SVD and Normalized Feature Domain

Abstract

ABSTRACTMost existing remote sensing image watermarking algorithms concentrate on excavation of particular embedding templates, image features, or geometric invariant domains, which present challenges in terms of resistance to desynchronization attacks, embedding domain repetition, and insufficient algorithm versatility. To address these issues, this study proposes a watermarking algorithm that is robust to desynchronization attacks and can adapt to different types of remote sensing images using the geometric invariant domain and hybrid frequency domain. The algorithm uses the multi‐scale SIFT to identify feature points in remote sensing images, then creates a Delaunay triangulation network (DTN) based on these feature points, extracts the tangent circles of triangles, and normalizes these tangent circles using image moment and affine transformation, and the feature domains with geometric invariance are constructed. On this basis, the discrete wavelet transform (DWT) transforms the feature domain to the frequency decomposition state, and the singular value decomposition (SVD) further mines the watermark embedding domain, ensuring the stability of the watermark transforming back and forth in the embedding domain and improving the overall invisibility of the watermarking algorithm. The experimental results indicate that, compared to related algorithms, the proposed watermarking algorithm not only adapts better to remote sensing images with different bands and bit depths but also provides superior invisibility and demonstrates strong robustness against various desynchronization attacks such as splicing, panning, rotating, as well as image processing like noise addition, filtering, and compression.