Presentation + Paper
14 June 2023 Intra-class data augmentation with deep generative models of threat objects in baggage radiographs
Heidi Komkov, Matthew Marshall, Erik Brubaker
Author Affiliations +
Abstract
Despite state-of-the-art deep learning-based computer vision models achieving high accuracy on object recognition tasks, x-ray screening of baggage at checkpoints is largely performed by hand. Part of the challenge in automation of this task is the relatively small amount of available labeled training data. Furthermore, realistic threat objects may have forms or orientations that do not appear in any training data, and radiographs suffer from high amounts of occlusion. Using deep generative models, we explore data augmentation techniques to expand the intra-class variation of threat objects synthetically injected into baggage radiographs using openly available baggage x-ray datasets. We also benchmark the performance of object detection algorithms on raw and augmented data.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Heidi Komkov, Matthew Marshall, and Erik Brubaker "Intra-class data augmentation with deep generative models of threat objects in baggage radiographs", Proc. SPIE 12531, Anomaly Detection and Imaging with X-Rays (ADIX) VIII, 1253108 (14 June 2023); https://doi.org/10.1117/12.2664022
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Radiography

X-rays

Object detection

X-ray imaging

Deep learning

Back to Top