The College of Education for Pure Sciences, Department of Computer Science, discussed a master’s thesis on a secure content-based image retrieval system using deep learning
The message submitted by the researcher (Miqdam Abdel Wahed Muhammad) included:
  In the era of digitalization, there is an urgent need for advanced mechanisms for effective image retrieval. This research addresses the important challenge of navigating large image repositories through Content-Based Image Retrieval (CBIR) systems. The main objective of this study is to improve CBIR systems by enhancing their accuracy and security. This was achieved by incorporating advanced deep learning models, specifically Ensemble Learning, Inception, MobileNet, and Xception, to efficiently extract features and incorporating cryptography to protect sensitive data from unauthorized access. The importance of this study lies in its ability to address the challenges of accurately retrieving relevant images from large datasets while ensuring data security. The Ensemble Learning model, in particular, demonstrated superior feature extraction performance, significantly improving image retrieval accuracy. The integrity of encryption adds a vital layer of security, making this approach highly relevant for applications that require secure and efficient image retrieval. This research not only advances CBIR technology, but also lays the foundation for future developments in this field, emphasizing the critical need for accuracy and security in image data handling in various fields.