A master's thesis at the College of Computer Science and Information Technology at University of Basrah examines the detection of live fingerprints using a deep learning framework.

The thesis, presented by Aya Abdulkarim Hamid, a graduate student in the Department of Computer Information Systems, aims to propose a lightweight deep learning network based on the ResNet architecture to distinguish between real and fake fingerprints. This approach boasts strong generalization capabilities while reducing computational complexity, enabling higher accuracy compared to current methods for detecting fake fingerprints.

The thesis also explores the network's ability to prevent unauthorized access, thereby enhancing overall system security. Its lightweight design also makes it suitable for real-world applications such as mobile devices or embedded systems with limited resources.