A Novel DNN-based Image Watermarking Algorithm
Data
2023
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
DNN architecture for image watermarking that balances the tasks
of embedding and detecting a watermark is presented. The system consists
of two networks: the embedder and the detector. A loss function based on
a structural similarity index measure minimizes the difference between the
original and watermarked signal. The average SSIM is 0.98 while the accuracy
is 99.99%.
Opis
Słowa kluczowe
deep neural networks, image watermarking, autoencoder, ssim, głębokie sieci neuronowe, znak wodny obrazu, autoenkoder, ssim
Cytowanie
Kovačević S., Pavlović K., Djurović I., A Novel DNN-based Image Watermarking Algorithm. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A.
(Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 301-306, ISBN 978-83-66741-92-8,
doi: 10.34658/9788366741928.48.