EUVIMEDEUVIMED entdecken
Crossref

A synchronization correction scheme based on random forest and GGD distribution for color image watermarking

Fu-ya Du, Xiu-fang Feng, Chun-peng Wang, Shuang Zhou, Hao Zhang

Physica Scripta · 20.03.2026 · 101 (11) · 115207

DOI: 10.1088/1402-4896/ae4f31 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 19.03.2026. Verfasst von Fu-ya Du und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Resistance to geometric attacks is a major obstacle for robust digital watermarking, as it severely compromises the synchronized information within the watermark, leading to extraction failure. Accordingly, this study proposes a robust color image watermarking algorithm based on random forest regression and the generalized Gaussian distribution (GGD). This method embeds a watermark into the low-frequency subband of the Cb component in color images. During embedding, DCT blocks are sorted based on the fuzzy concept. Before extracting the watermark, the attacked image undergoes geometric correction using parameters estimated by random forest model. The feature vectors for training this model are derived by modeling the Shearlet transform coefficients of training images with a GGD distribution. Addressing the current issue where watermarking technologies often prioritize performance enhancement while neglecting the security of the embedding process, the algorithm incorporates a new chaotic map named 2D-SCHM and designs a symmetric encryption algorithm based on the Feistel network architecture for watermark encryption. Experiments demonstrate that the PSNR value of the embedded watermark image exceeds 49 dB, and the NC value for extracting the watermark against most attacks surpasses 0.91, achieving both high imperceptibility and robustness against attacks.

Zitieren

APA

Du, F., Feng, X., Wang, C., Zhou, S., & Zhang, H. (2026). A synchronization correction scheme based on random forest and GGD distribution for color image watermarking. Physica Scripta, 101(11), 115207. https://doi.org/10.1088/1402-4896/ae4f31

Vancouver

Du F, Feng X, Wang C, Zhou S, Zhang H. A synchronization correction scheme based on random forest and GGD distribution for color image watermarking. Physica Scripta. 2026;101(11):115207. doi:10.1088/1402-4896/ae4f31

BibTeX
@article{Du2026,
  author = {Du, Fu-ya and Feng, Xiu-fang and Wang, Chun-peng and Zhou, Shuang and Zhang, Hao},
  title = {A synchronization correction scheme based on random forest and GGD distribution for color image watermarking},
  journal = {Physica Scripta},
  year = {2026},
  volume = {101},
  number = {11},
  pages = {115207},
  doi = {10.1088/1402-4896/ae4f31}
}
Kostenlos starten →