Pre-Thesis Seminar for Master’s Student Mohammed Majid Jabr Jawad in the Department of Software

Duhaa Fadill Abbas
As part of the ongoing scientific activities at the Department of Software – College of Information Technology, University of Babylon, Master’s student Mohammed Majid Jabr Jawad presented his pre-thesis seminar to discuss his proposed research titled:
“A Proposed Data Hiding System Based on Deep Learning Techniques and Texture Context”, under the supervision of Prof. Dr. Tawfiq Abdulkhaliq Abbas, and in the presence of the department’s scientific committee.

The research aims to develop an intelligent data hiding (Steganography) system for digital images, leveraging the advanced capabilities of deep learning techniques and texture-context analysis to achieve a high level of security without compromising image quality.

The proposed system utilizes the MiDaS model to extract the depth map from the original image, followed by identifying keypoints using the Shi-Tomasi algorithm and constructing a triangular mesh through Delaunay Triangulation. Subsequently, the statistical correlation between the pixels within each triangle is calculated using Spearman’s rank correlation coefficient, to determine the optimal number of bits that can be embedded securely and imperceptibly.

The study demonstrated promising results, with the system achieving a high Peak Signal-to-Noise Ratio (PSNR) exceeding 58 dB, along with flexible and secure embedding capacity. This work contributes to advancing the field of digital information security and offers potential applications in protecting sensitive data and enhancing digital privacy.