Detection threshold selection for correlation based digital image watermarks through F-score optimization | Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitelnaja tehnika i informatika – Tomsk State University Journal of Control and Computer Science. 2025. № 72. DOI: 10.17223/19988605/72/6

Detection threshold selection for correlation based digital image watermarks through F-score optimization

The approach for selecting the detection threshold for correlation based digital image watermarks is proposed. The watermark detection process is treated as a binary classification problem, enabling the use of the F-score as a quality metric. Within this framework, the optimal detection threshold corresponds to the maximum F-score value. The F-score is computed over a set of test images and a predefined set of operations that simulate distortions introduced during transmission or watermark removal attacks. Methods for improving the computational efficiency of F-score maximization are proposed. The proposed approach to choosing a threshold value is compared with the statistical method. Contribution of the authors: the authors contributed equally to this article. The authors declare no conflicts of interests.

Download file

Keywords

digital watermark, F-score, detection threshold, content protection

Authors

Name	Organization	E-mail
Anzhin Viktor A.	National Research Tomsk State University	viktor.anjin@gmail.com
Trenkaev Vadim N.	National Research Tomsk State University	kziiktvn@gmail.com

Всего: 2

References

Грибунин В.Г., Оков И.Н., Туринцев И.В. Цифровая стеганография. М. : СОЛОН-Пресс, 2016. 262 с.

Cox I.J., Miller M.L., Bloom J.A. Watermarking applications and their properties // Proc.Int. Conf. on Information Technology: Coding and Computing (Cat. No. PR00540). IEEE, 2000. P. 6-10.

Wan W. et al. A comprehensive survey on robust image watermarking // Neurocomputing. 2022. V. 488. P. 226-247. doi: 10.1016/j.neucom.2022.02.083.

Cox I. et al. Digital watermarking and steganography. Morgan Kaufmann, 2007. xxviii, 593 р.

Cox I. J. et al. Secure spread spectrum watermarking for multimedia // IEEE Transactions on Image Processing. 1997. V. 6 (12). P. 1673-1687.

Barni M. et al. A DCT-domain system for robust image watermarking // Signal Processing. 1998. V. 66 (3). P. 357-372.

Cox I.J. et al. Secure spread spectrum watermarking for images, audio and video // Proc. of 3rd IEEE Int. Conf. on Image Processing. 1996. V. 3. P. 243-246.

Jabade V.S., Gengaje S.R. Literature review of wavelet based digital image watermarking techniques // Int. J. of Computer Appli cations. 2011. V. 31 (7). P. 28-35.

Thanki R.M., Kher R.K., Vyas D.D. Robustness of correlation based watermarking techniques using WGN against different order statistics filters // Int. J. of Computer Science and Telecommunications. 2011. V. 2 (4). P. 45-49.

Piva A. et al. Threshold selection for correlation-based watermark detection // Proc. of COST. 1998. V. 254. P. 67-72.

Briassouli A., Strintzis M.G. Locally optimum nonlinearities for DCT watermark detection // IEEE Transactions on Image Processing. 2004. V. 13 (12). P. 1604-1617.

Wang J. et al. Locally optimum detection for Barni's multiplicative watermarking in DWT domain // Signal Processing. 2008. V. 88 (1). P. 117-130.

Kwon S.G. et al. Watermark detection algorithm using statistical decision theory // Proc. IEEE Int. Conference on Multimedia and Expo. 2002. V. 1. P. 561-564.

Powers D.M.W. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation // arXiv. 2010. Art. 16061. doi: 10.48550/arXiv.2010.16061.

Watermark Detection Threshold Selection // github.com. URL: https://github.com/anjin-viktor/watermark-detection-threshold-selection (accessed: 09.02.2025).

Rashtchian C. et al. Collecting image annotations using amazon’s mechanical turk // Proc. of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk. 2010. С. 139-147.

A complete, cross-platform solution to record, convert and stream audio and video // FFmpeg. URL: ffmpeg.org (accessed: 09.02.2025).

Press W., Teukolsky S.A., Vetterling W.T., Flannery B.P. Numerical Recipes in C. Cambridge et al. : Cambridge University Press, 1988. xxvi, 994 р.

Brent R.P. Algorithms for minimization without derivatives. Courier Corporation, 2013.

Plummer B.A. et al. Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models // Proc. of the IEEE Int. Conf. on Computer Vision. 2015. P. 2641-2649.

Формат изображения для Интернета. URL: https://developers.google.com/speed/webp (дата обращения: 09.02.2025).