INCREASING THE EFFICIENCY OF THE STEGANOGRAPHIC SYSTEM THROUGH THE USE OF IMAGE PROCESSING METHODS

DOI: 10.31673/2409-7292.2025.030871

Abstract

The development of computer networks has led to an increase in the volume of information transmitted over them and,
quite often, requires protection from unauthorized access. Along with cryptographic methods, steganographic methods of hiding
information are actively developing. The effectiveness of a steganographic system depends on many factors. Among them, the
semantic content of the stegocontainer image and the methods of implementing the algorithm itself should be highlighted. To a
much lesser extent, the scientific literature has paid attention to the study of the influence of stegocontainer processing methods
on the effectiveness of the stegosystem. This work proposes a modified generalized model of a steganographic system, which
contains two additional blocks - a block of improvement methods and a block of reference efficiency criteria. Before hiding, the
stegocontainer is processed by pre-processing methods – improvement, dynamic range correction, noise removal, etc. and
checked for compliance with the efficiency criteria of stegosystems. The approximate values of the listed efficiency criteria are
obtained on the basis of statistical data. As a result of the conducted research, it was confirmed that the methods of hiding in the
frequency domain (DCT, YASS) are more effective compared to the methods of embedding in the spatial domain (LSB).
Methods using neural networks (CNN, U-Net) are even more effective. Experimental modeling of the influence of noise and
blurring of the stegocontainer on the main parameters of the efficiency of the steganosystem using the LSB algorithm was
carried out. It was established that the method of embedding in the least significant bit, due to the adaptability of concealment,
provides high visual quality of images even after embedding a large text message and in the presence of blurring. Impulse noise
significantly reduces the visual quality of perception. Also, the preservation of hidden information is negatively affected by
information compression, especially in the case of using embedding methods in the spatial domain.
Keywords: steganosystem efficiency, image processing, information protection, neural networks, spatial and frequency
domain.

References
1. Журавель Ю. І., Мичуда Л. З. Підвищення ефективності стеганографії через застосування методів
покращання зображень та моделей штучного інтелекту // Сучасний захист інформації. 2025. № 2(62). С. 59–67.
DOI: 10.31673/2409-7292.2025.023202.
2. Gonzalez R., Woods R. Digital image processing. 2nd ed. NJ: Prentice Hall, 2002.
3. Салімонович А. О., Гармаш В. В. Метод фільтрації цифрових зображень на основі білатерального
фільтру : дис. … д-ра техн. наук. Вінниця : ВНТУ, 2024.
4. Gao C., Song C., Zhang Y., Qi D., Yu Y. Improving the performance of infrared and visible image fusion based
on latent low-rank representation nested with rolling guided image filtering // IEEE Access. 2021. Vol. 9. P. 91462-91475.
5. Zhang D., He Z., Zhang X., Wang Z., Ge W., Shi T., Lin Y. Underwater image enhancement via multi-scale
fusion and adaptive color-gamma correction in low-light conditions // Engineering Applications of Artificial Intelligence.
2023. Vol. 126. Article ID 106972.
6. Cai Y., Bian H., Lin J., Wang H., Timofte R., Zhang Y. Retinexformer: One-stage retinex-based transformer for
low-light image enhancement // Proc. IEEE/CVF Int. Conf. on Computer Vision. 2023. P. 12504-12513.
7. Shah M., Khan M., Khan S. S., Ali S. Multi-Focus Image Fusion using Unsharp Masking with Discrete Cosine
Transform. 2023. [Електронний ресурс].
8. Halidou A., Mohamadou Y., Ari A. A. A., Zacko E. J. G. Review of wavelet denoising algorithms // Multimedia
Tools and Applications. 2023. Vol. 82, No. 27. P. 41539-41569.
9. Zhang C., Yen K. S. A Refined First-Order Sparse TGV Model with L1 Norm Data Fidelity for Enhanced
Image Denoising // Int. Symp. on Systems Modelling and Simulation. Singapore : Springer Nature Singapore, 2024. P. 1-
13.
10. Alnuaimy A. N., Jawad A. M., Abdulkareem S. A., Mustafa F. M., Ivanchenko S., Toliupa S. BM3D denoising
algorithms for medical image // 2024 35th Conf. of Open Innovations Association (FRUCT). IEEE, 2024. P. 135–141.
11. Журавель Ю. І., Мичуда Л. З. Метод кількісного оцінювання візуальної якості цифрових кольорових
зображень // Сучасний захист інформації. 2024. № 4(60). С. 39-45. DOI: 10.31673/2409-7292.2024.040004.
12. Хорошко В. О., Яремчук Ю. Є., Карпінець В. В. Комп’ютерна стеганографія. Вінниця : ВНТУ, 2017.
244 с.
13. Treder M. S., Codrai R., Tsvetanov K. A. Quality assessment of anatomical MRI images from generative
adversarial networks: Human assessment and image quality metrics // Journal of Neuroscience Methods. 2022. Vol. 374.
Article ID 109579.
14. Neißner A., Mäder U., Fiebich M. Enhancing clinical CT image quality assessment: adapting no-reference
methods NIQE and BRISQUE // Medical Imaging 2025: Physics of Medical Imaging. 2025. Vol. 13405. P. 903-911.