Automatic Threat Prediction of Body-Worn Objects for Security Screening Purposes

Abstract

Fast detection of hazardous objects in millimeter-wave personnel screening can increase the operating efficiency of secure environments. In airports, accurate automatic detection and classification of body-worn objects can reduce the number of pat-downs while keeping the transportation environment safe and secure. Since many benign objects, such as paper and leather, are lossy materials, being able to characterize them and set them aside from the secondary checks will significantly reduce the screening process time. In this article, we introduce an effective image-processing-based method for characterizing lossy materials that might be concealed under clothing at checkpoints. The method has been combined with a modified version of the previously developed algorithm that can be used specifically to characterize lossless materials. The proposed algorithm can automatically distinguish lossless materials from lossy ones and calculate their thickness and permittivities. Starting from the radar reconstructed image showing a cross section of the body, we extract the nominal body contour using the Fourier series, separate body, and object responses, categorize the object as lossy or lossless based on the depression and protrusion of the body contour, and, finally, predict possible values for the object’s permittivity and thickness. Our resulting classification is good, implying fewer nuisance alarms at checkpoints.