Automated Threat Detection in X-ray imagery for Advanced Border and Access Security: Challenges and Solutions

一、主讲人：Naoufel Werghi

二、时　间：14：30 - 15：30

三、地　点：沙河校区主楼东302

四、主持人：信息与软件工程学院　江维教授

五、内容简介：

The continual increase in air travel has led to a growing concern regarding safety and security. To address this, security personnel at ports currently conduct manual inspections of incoming and outgoing passenger luggage, packages, and containers using x-ray scanners. However, this screening process is resource-intensive and demands constant vigilance from human experts. This approach introduces the risk of human error, stemming from factors such as fatigue, challenges in identifying contraband items, the need for rapid decision-making, and varying levels of experience among staff. In this talk, we present recent computer vision and machine learning frameworks developed to automatically detect contraband items in scanned X-ray images of passenger baggage. We highlight innovative approaches that address key challenges, including the lack of texture in X-ray imagery, cluttered scenes, severe class imbalance, and the integration of textual descriptions into the detection pipeline.
七、主讲人简介：

Dr. Naoufel Werghi holds a Research Habilitation and a Ph.D. in Computer Vision from the University of Strasbourg. He is currently a Full Professor in the Department of Computer Science at Khalifa University, where he leads the Artificial Intelligence and Big Data theme within the Center of Secure Cyber-Physical Systems. He is also the founder of the Computer Vision and Machine Intelligence Lab, and found and CEO of IBSAR technologies. Dr. Werghi's primary research focus is on 2D/3D image and video analysis and interpretation, having led multiple funded projects in areas such as biometrics, medical imaging robotics, surveillance, inspection, and intelligent systems. He serves as an Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology, IEEE Journal of Biomedical and Health Informatics, and the Eurasip Journal on Image and Video Processing.