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),
| Name | Country | City | Type |
|---|
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Datasets
| ID | Title | Public URL |
|---|
Dataset collections
| ID | Acronym | Title | Public URL |
|---|
Scripts / source codes
| Description | Public URL |
|---|
Additional supporting files
| File name | Description | File type |
|---|