# The Good, the Bad and the Ugly: Evaluating Convolutional Neural Networks for Prohibited Item Detection Using Real and Synthetically Composited X-ray Imagery

Source: [The Good, the Bad and the Ugly: Evaluating Convolutional Neural Networks for Prohibited Item Detection Using Real and Synthetically Composited X-ray Imagery](<https://www.sota2.com/research/paper/68fa66761e209131cea10484>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:50:28.993Z

Authors: Neelanjan Bhowmik, Qian Wang, Yona Falinie A. Gaus, Marcin Szarek, Toby P. Breckon

Published: 2019-09-25T14:16:16.000Z

## Abstract

Detecting prohibited items in X-ray security imagery is pivotal in maintaining border and transport security against a wide range of threat profiles. Convolutional Neural Networks (CNN) with the support of a significant volume of data have brought advancement in such automated prohibited object detection and classification. However, collating such large volumes of X-ray security imagery remains a significant challenge. This work opens up the possibility of using synthetically composed imagery, avoiding the need to collate such large volumes of hand-annotated real-world imagery. Here we investigate the difference in detection performance achieved using real and synthetic X-ray training imagery for CNN architecture detecting three exemplar prohibited items, {Firearm, Firearm Parts, Knives}, within cluttered and complex X-ray security baggage imagery. We achieve 0.88 of mean average precision (mAP) with a Faster R-CNN and ResNet-101 CNN architecture for this 3-class object detection using real X-ray imagery. While the performance is comparable with synthetically composited X-ray imagery (0.78 mAP), our extended evaluation demonstrates both challenge and promise of using synthetically composed images to diversify the X-ray security training imagery for automated detection algorithm training.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1909.11508>)

[PDF](<https://arxiv.org/pdf/1909.11508.pdf>)
