Abstract:
Within the field of steganography, image steganography is a fascinating technique
that hides confidential data behind a cover image. However, the quality and security
of hidden content are threatened by potential degradation introduced by the transmis sion of stego images, which can take the form of noise, blurring, or sharpening. In this
research endeavor, we present an innovative approach by integrating image degrada tion models into an existing state-of-the-art invertible image-in-image steganography
model known as HiNet. Our proposed methodology involves applying a degradation
model to the stego image post-secret image embedding, followed by the usual secret
image extraction. By introducing these additional layers to the steganographic pro cess, we aim to enhance the robustness of our model against various degradation sce narios, such as Gaussian noise, blurring, and sharpening. By using knowledge from
cutting-edge architectures such as HiNet, we aim to improve the overall security and
quality of hidden pictures. We performed experiments on HiNet and achieved im proved results in handling degradations like noise, blurring, and sharpening.
Description:
Supervised by
Dr. Md. Hasanul Kabir,
Professor,
Co-supervisor
Mr. Shahriar Ivan,
Lecturer,
Department of Computer Science and Engineering (CSE)
Islamic University of Technology (IUT)
Board Bazar, Gazipur, Bangladesh
This thesis is submitted in partial fulfillment of the requirement for the degree of Bachelor of Science in Software Engineering, 2024