Operator Assisted Threat Assessment for Carry-On
Besma R. Abidi, Mark Mitckes, Mongi A. Abidi, Andreas Koschan
Imaging, Robotics, and Intelligent Sytems Laboratory
334 Ferris Hall, University of Tennessee
Knoxville, TN 37996-2100
Abstract: A summary of activities at the University of Tennessee's Imaging, Robotics and Intelligent
Systems (IRIS) Laboratory in the area of threat detection for airport luggage inspection is proposed.
Starting with the raw original image, a number of image enhancement techniques (linear regression, non-
linear intensity adjustment, histogram equalization, etc.) were implemented and evaluated for the purpose
of increasing contrast and adjusting brightness to make the various components of the luggage scene
more distinct. In addition, scene de-cluttering techniques (linear image hashing, non-linear image
hashing, and edge-based segmentation) were tested for the purpose of hopefully making screener
decisions easier and faster. Lastly, techniques for color-coding and visualizing X-ray data via graphical
user interfaces for effective detection of threat objects were investigated.
Luggage inspection is an essential process for airports and airplane security because of the presence of