Authors: Najia Trache, Mohammed Salem, Mohamed Fayçel Khelfi
Keywords: Forensic-Based Investigation (FBI), Robustness and Imperceptibility, Image Watermarking, Singular Value Decomposition, Normalized Correlation Coefficient, Discrete Wavelet Transformation.
Abstract
In recent years, image watermarking has become the most active research in the information hiding field. This paper presents an application of a computational intelligence technique to obtain robust and secure image-watermarking schemes for data image transmission. The optimization goal is achieved via a new robust method based on the hybridization (in the digital domain) of the image-watermarking scheme using Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD). The Forensic-Based Investigation (FBI) optimization algorithm is considered to search for the best scaling factor and the appropriate location for the watermark insertion. The Arnold Transform (AT) encryption is also introduced to enhance the watermark image process security. To show the efficiency of the proposed schemes, several watermarked images are subjected to several attacks, and their imperceptibility and robustness are checked via structural similarity index measure (SSIM) and Normalized Correlation Coefficient (NCC) where the proposed schemes provide competitive simulation results. Statistical analysis is also carried out to prove the performance of the used optimization algorithm.
DOI
https://doi.org/10.56415/csjm.v32.13
Fulltext
![Adobe PDF document](/i/pdf.gif)
–
1.24 Mb