Automated detection of inorganic powders in X-ray images of airport luggage

At the checkpoint, the detection of illicit inorganic powders in passenger luggage using conventional X-ray can be challenging. We present the first published algorithm for automated detection of inorganic powder-like substances from X-ray images of realistically packed passenger bags using computer vision. The proposed method utilizes machine learning (SVM) classifiers built from texture Local Binary Patterns (LBP) features. When tested on a dataset created in-house at JRC, the algorithm achieves a detection precision of 97% and a false positive detection rate of 3%. This is the first study performed on a realistic dataset, including different amounts and shapes of powders and electronic clutter, and where the success of the automated method is compared with inter-observer variability.

VUKADINOVIC Danijela;  RUIZ OSES Miguel;  ANDERSON David; 

2023-06-07

SPRINGER NATURE

JRC132597

1938-7741 (online),   

https://doi.org/10.1007/s12198-023-00261-5,    https://publications.jrc.ec.europa.eu/repository/handle/JRC132597,   

10.1007/s12198-023-00261-5 (online),