Threat Objects Detection in X-ray Images Using an Active Vision Approach

Abstract

X-ray testing for baggage inspection has been increasingly used at airports, reducing the risk of terrorist crimes and attacks. Nevertheless, this task is still being carried out by human inspectors and with limited technological support. The technology that is being used is not always effective, as it depends mainly on the position of the object of interest, occlusion, and the accumulated experience of the inspector. Due to this problem, we have developed an approach that inspects X-ray images using active vision in order to automatically detect objects that represent a threat. Our method includes three steps: detection of potential threat objects in single views based on the similarity of features and spatial distribution; estimation of the best-next-view using Q-learning; and elimination of false alarms based on multiple view constraints. We tested our algorithm on X-ray images that included handguns and razor blades. In the detection of handguns we registered good results for recall and precision (Re = 67%, Pr = 83%) along with a high performance in the detection of razor blades (Re = 82%, Pr = 100%) taking into consideration 360 inspections in each case. Our results indicate that non-destructive inspection actively using X-ray images, leads to more effective object detection in complex environments, and helps to offset certain levels of occlusion and the internal disorder of baggage.