Authors:
Souha Mansour
1
;
Saoussen Ben Jabra
2
and
Ezzedine Zagrouba
1
Affiliations:
1
High Institute of Computer Science, University of Tunis El Manar, 2 Rue Abou Rayhane Bayrouni, Tunis, Tunisia
;
2
National Engineering School of Sousse, University of Sousse, BP 264 Riadh, Sousse, Tunisia
Keyword(s):
Deep Learning, CNN, Mosaic Generation, Video Watermarking, Embedding Network, Attack Simulation.
Abstract:
Recently, digital watermarking has benefited from the rise of deep learning and machine learning approaches. Even while effective deep learning-based watermarking techniques have been proposed for images, video still introduces extra difficulties, such as motion, temporal consistency, and spatial location. In this paper, a robust and imperceptible deep-learning-based video watermarking method based on CNN architecture and mosaic generation is suggested. The proposed approach is decomposed into two main steps: mosaic generation and signature embedding. This last one includes four stages: pre-processing networks for both the obtained mosaic and the watermark, embedding network, attack simulation, and extraction network. In fact, the main purpose of mosaic generation is to create an image from the original video and to provide robustness against malicious attacks, particularly against collusion attacks. CNN architecture is used to embed signature to maximize invisibility and robustness
compromise. The proposed solution outperforms both traditional video watermarking and deep learning video watermarking, according to experimental evaluations on a variety of distortions.
(More)