Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items

Muhammad Shafay; Taimur Hassan; Divya Velayudhan; Ernesto Damiani; Naoufel Werghi

doi:10.1007/978-3-030-73689-7_53

Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items

Muhammad Shafay, Taimur Hassan, Divya Velayudhan, Ernesto Damiani, Naoufel Werghi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

Automatic detection of prohibited items in passenger baggage is a challenging task, especially in cluttered and occluded concealment scenarios. In this paper, we present a deep fusion driven semantic segmentation network that leverages multi-scale feature representations (extracted via CNN backbone) to generate highly accurate segmentation masks of the suspicious items irrespective of the clutter and concealment. Assessed with the public GDXray, SIXray and OPIXray datasets our proposed architecture reached a mean IoU performance of 0.7768, 0.6263, and 0.6713 respectively, outperforming the leading frameworks.

Original language	British English
Title of host publication	Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020
Editors	Ajith Abraham, Yukio Ohsawa, Niketa Gandhi, M. A. Jabbar, Abdelkrim Haqiq, Seán McLoone, Biju Issac
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	550-559
Number of pages	10
ISBN (Print)	9783030736880
DOIs	https://doi.org/10.1007/978-3-030-73689-7_53
State	Published - 2021
Event	12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020 - Virtual, Online Duration: 15 Dec 2020 → 18 Dec 2020

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1383 AISC
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020
City	Virtual, Online
Period	15/12/20 → 18/12/20

Keywords

Aviation security
Convolutional neural networks
Object recognition
Semantic segmentation
X-ray baggage imagery

Access to Document

10.1007/978-3-030-73689-7_53

Cite this

Shafay, M., Hassan, T., Velayudhan, D., Damiani, E., & Werghi, N. (2021). Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items. In A. Abraham, Y. Ohsawa, N. Gandhi, M. A. Jabbar, A. Haqiq, S. McLoone, & B. Issac (Eds.), Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 (pp. 550-559). (Advances in Intelligent Systems and Computing; Vol. 1383 AISC). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-73689-7_53

Shafay, Muhammad ; Hassan, Taimur ; Velayudhan, Divya et al. / Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items. Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020. editor / Ajith Abraham ; Yukio Ohsawa ; Niketa Gandhi ; M. A. Jabbar ; Abdelkrim Haqiq ; Seán McLoone ; Biju Issac. Springer Science and Business Media Deutschland GmbH, 2021. pp. 550-559 (Advances in Intelligent Systems and Computing).

@inproceedings{5e4a0dcf0d9f413bbff702dbb47c613e,

title = "Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items",

abstract = "Automatic detection of prohibited items in passenger baggage is a challenging task, especially in cluttered and occluded concealment scenarios. In this paper, we present a deep fusion driven semantic segmentation network that leverages multi-scale feature representations (extracted via CNN backbone) to generate highly accurate segmentation masks of the suspicious items irrespective of the clutter and concealment. Assessed with the public GDXray, SIXray and OPIXray datasets our proposed architecture reached a mean IoU performance of 0.7768, 0.6263, and 0.6713 respectively, outperforming the leading frameworks.",

keywords = "Aviation security, Convolutional neural networks, Object recognition, Semantic segmentation, X-ray baggage imagery",

author = "Muhammad Shafay and Taimur Hassan and Divya Velayudhan and Ernesto Damiani and Naoufel Werghi",

note = "Funding Information: Acknowledgement. This research work is enabled by the research fund from ADEK Ref: AARE19-156 and a Khalifa University: Ref: CIRA-2019-047. Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020 ; Conference date: 15-12-2020 Through 18-12-2020",

year = "2021",

doi = "10.1007/978-3-030-73689-7_53",

language = "British English",

isbn = "9783030736880",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "550--559",

editor = "Ajith Abraham and Yukio Ohsawa and Niketa Gandhi and Jabbar, {M. A.} and Abdelkrim Haqiq and Se{\'a}n McLoone and Biju Issac",

booktitle = "Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020",

address = "Germany",

}

Shafay, M, Hassan, T, Velayudhan, D, Damiani, E & Werghi, N 2021, Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items. in A Abraham, Y Ohsawa, N Gandhi, MA Jabbar, A Haqiq, S McLoone & B Issac (eds), Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020. Advances in Intelligent Systems and Computing, vol. 1383 AISC, Springer Science and Business Media Deutschland GmbH, pp. 550-559, 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020, Virtual, Online, 15/12/20. https://doi.org/10.1007/978-3-030-73689-7_53

Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items. / Shafay, Muhammad; Hassan, Taimur; Velayudhan, Divya et al.
Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020. ed. / Ajith Abraham; Yukio Ohsawa; Niketa Gandhi; M. A. Jabbar; Abdelkrim Haqiq; Seán McLoone; Biju Issac. Springer Science and Business Media Deutschland GmbH, 2021. p. 550-559 (Advances in Intelligent Systems and Computing; Vol. 1383 AISC).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items

AU - Shafay, Muhammad

AU - Hassan, Taimur

AU - Velayudhan, Divya

AU - Damiani, Ernesto

AU - Werghi, Naoufel

N1 - Funding Information: Acknowledgement. This research work is enabled by the research fund from ADEK Ref: AARE19-156 and a Khalifa University: Ref: CIRA-2019-047. Publisher Copyright: © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2021

Y1 - 2021

N2 - Automatic detection of prohibited items in passenger baggage is a challenging task, especially in cluttered and occluded concealment scenarios. In this paper, we present a deep fusion driven semantic segmentation network that leverages multi-scale feature representations (extracted via CNN backbone) to generate highly accurate segmentation masks of the suspicious items irrespective of the clutter and concealment. Assessed with the public GDXray, SIXray and OPIXray datasets our proposed architecture reached a mean IoU performance of 0.7768, 0.6263, and 0.6713 respectively, outperforming the leading frameworks.

AB - Automatic detection of prohibited items in passenger baggage is a challenging task, especially in cluttered and occluded concealment scenarios. In this paper, we present a deep fusion driven semantic segmentation network that leverages multi-scale feature representations (extracted via CNN backbone) to generate highly accurate segmentation masks of the suspicious items irrespective of the clutter and concealment. Assessed with the public GDXray, SIXray and OPIXray datasets our proposed architecture reached a mean IoU performance of 0.7768, 0.6263, and 0.6713 respectively, outperforming the leading frameworks.

KW - Aviation security

KW - Convolutional neural networks

KW - Object recognition

KW - Semantic segmentation

KW - X-ray baggage imagery

UR - http://www.scopus.com/inward/record.url?scp=85105863528&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-73689-7_53

DO - 10.1007/978-3-030-73689-7_53

M3 - Conference contribution

AN - SCOPUS:85105863528

SN - 9783030736880

T3 - Advances in Intelligent Systems and Computing

SP - 550

EP - 559

BT - Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020

A2 - Abraham, Ajith

A2 - Ohsawa, Yukio

A2 - Gandhi, Niketa

A2 - Jabbar, M. A.

A2 - Haqiq, Abdelkrim

A2 - McLoone, Seán

A2 - Issac, Biju

PB - Springer Science and Business Media Deutschland GmbH

T2 - 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020

Y2 - 15 December 2020 through 18 December 2020

ER -

Shafay M, Hassan T, Velayudhan D, Damiani E , Werghi N. Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items. In Abraham A, Ohsawa Y, Gandhi N, Jabbar MA, Haqiq A, McLoone S, Issac B, editors, Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020. Springer Science and Business Media Deutschland GmbH. 2021. p. 550-559. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-73689-7_53

Deep Fusion Driven Semantic Segmentation for the Automatic Recognition of Concealed Contraband Items

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this