Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images

Threat detection in X-ray security images is critical for preserving public safety. Recently, deep learning algorithms have begun to be adopted for threat detection tasks in X-ray security images. However, most of the prior works in this field have largely focused on using image-level classification...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Joanna Kazzandra Dumagpi, Yong-Jin Jeong
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	X-ray threat detection semantic segmentation instance segmentation deep learning security Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/d9b2c6f96ee047ee9290f62a77c0a293
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d9b2c6f96ee047ee9290f62a77c0a293
record_format	dspace
spelling	oai:doaj.org-article:d9b2c6f96ee047ee9290f62a77c0a2932021-11-11T15:17:53ZPixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images10.3390/app1121102612076-3417https://doaj.org/article/d9b2c6f96ee047ee9290f62a77c0a2932021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10261https://doaj.org/toc/2076-3417Threat detection in X-ray security images is critical for preserving public safety. Recently, deep learning algorithms have begun to be adopted for threat detection tasks in X-ray security images. However, most of the prior works in this field have largely focused on using image-level classification and object-level detection approaches. Adopting object separation as a pixel-level approach to analyze X-ray security images can significantly improve automatic threat detection. In this paper, we investigated the effects of incorporating segmentation deep learning models in the threat detection pipeline of a large-scale imbalanced X-ray dataset. We trained a Faster R-CNN (region-based convolutional neural network) model to localize possible threat regions in the X-ray security images on a balanced dataset to maximize detection of true positives. Then, we trained a DeepLabV3+ model to verify the preliminary detections by classifying each pixel in the threat regions, which resulted in the suppression of false positives. The two models were combined in one detection pipeline to produce the final detections. Experiment results demonstrate that the proposed method significantly outperformed previous baseline methods and end-to-end instance segmentation methods, achieving mean average precisions (m<i>AP</i>s) of 94.88%, 91.40%, and 89.42% across increasing scales of imbalance in the practical dataset.Joanna Kazzandra DumagpiYong-Jin JeongMDPI AGarticleX-raythreat detectionsemantic segmentationinstance segmentationdeep learningsecurityTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10261, p 10261 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	X-ray threat detection semantic segmentation instance segmentation deep learning security Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	X-ray threat detection semantic segmentation instance segmentation deep learning security Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Joanna Kazzandra Dumagpi Yong-Jin Jeong Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images
description	Threat detection in X-ray security images is critical for preserving public safety. Recently, deep learning algorithms have begun to be adopted for threat detection tasks in X-ray security images. However, most of the prior works in this field have largely focused on using image-level classification and object-level detection approaches. Adopting object separation as a pixel-level approach to analyze X-ray security images can significantly improve automatic threat detection. In this paper, we investigated the effects of incorporating segmentation deep learning models in the threat detection pipeline of a large-scale imbalanced X-ray dataset. We trained a Faster R-CNN (region-based convolutional neural network) model to localize possible threat regions in the X-ray security images on a balanced dataset to maximize detection of true positives. Then, we trained a DeepLabV3+ model to verify the preliminary detections by classifying each pixel in the threat regions, which resulted in the suppression of false positives. The two models were combined in one detection pipeline to produce the final detections. Experiment results demonstrate that the proposed method significantly outperformed previous baseline methods and end-to-end instance segmentation methods, achieving mean average precisions (m<i>AP</i>s) of 94.88%, 91.40%, and 89.42% across increasing scales of imbalance in the practical dataset.
format	article
author	Joanna Kazzandra Dumagpi Yong-Jin Jeong
author_facet	Joanna Kazzandra Dumagpi Yong-Jin Jeong
author_sort	Joanna Kazzandra Dumagpi
title	Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images
title_short	Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images
title_full	Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images
title_fullStr	Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images
title_full_unstemmed	Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images
title_sort	pixel-level analysis for enhancing threat detection in large-scale x-ray security images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d9b2c6f96ee047ee9290f62a77c0a293
work_keys_str_mv	AT joannakazzandradumagpi pixellevelanalysisforenhancingthreatdetectioninlargescalexraysecurityimages AT yongjinjeong pixellevelanalysisforenhancingthreatdetectioninlargescalexraysecurityimages
_version_	1718435589208932352

Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security Images

Ejemplares similares