Michel, S., Koller, S.M., de Ruiter, J.C., Moerland, R., Hogervorst, M. and Schwaninger, A. (2007) Computer-Based Training Increases Efficiency in X-Ray Image Interpretation by Aviation Security Screeners. 2007 41st Annual IEEE International Carnahan Conference on Security Technology, Ottawa, 8-11 October 2007, 201-206.
https://doi.org/10.1109/ccst.2007.4373490

has been cited by the following article:

• TITLE: Comparative Study of Four Classification Techniques for the Detection of Threats in Baggage from X-Ray Images

  AUTHORS: Boka Trinité Konan, Hyacinthe Kouassi Konan, Jules Allani, Olivier Asseu

  KEYWORDS: Deep Learning, Baggage Control, Convolutional Neural Networks, Image Filtering, Object Detection Algorithms, X-Ray Images, Autoencoder, Random Forests

  JOURNAL NAME: Open Journal of Applied Sciences, Vol.14 No.12, December 10, 2024

  ABSTRACT: Baggage screening is crucial for airport security. This paper examines various algorithms for firearm detection in X-ray images of baggage. The focus is on identifying steel barrel bores, which are essential for detonation. For this, the study uses a set of 22,000 X-ray scanned images. After preprocessing with filtering techniques to improve image quality, deep learning methods, such as Convolutional Neural Networks (CNNs), are applied for classification. The results are also compared with Autoencoder and Random Forest algorithms. The results are validated on a second dataset, highlighting the advantages of the adopted approach. Baggage screening is a very important part of the risk assessment and security screening process at airports. Automating the detection of dangerous objects from passenger baggage X-ray scanners can speed up and increase the efficiency of the entire security procedure.