Automatic detection of prohibited items with small size in X-ray images

In this paper, we focus on the detection of prohibited items with small size, and establish an automatic detection model based on feature fusion single shot multibox detector (FSSD) architecture. Two modifications are carried out to improve the detection accuracy. Firstly, the semantic enrichment mo...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Optoelectronics letters 2020-07, Vol.16 (4), p.313-317
Hauptverfasser:	Zhang, Yu-tao, Zhang, Hai-gang, Zhao, Teng-fei, Yang, Jin-feng
Format:	Artikel
Sprache:	eng
Schlagworte:	Architecture Computer simulation Convolution Feature extraction Image detection Lasers Low level Modules Optical Devices Optics Photonics Physics Physics and Astronomy Semantics Target detection
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	317
container_issue	4
container_start_page	313
container_title	Optoelectronics letters
container_volume	16
creator	Zhang, Yu-tao Zhang, Hai-gang Zhao, Teng-fei Yang, Jin-feng
description	In this paper, we focus on the detection of prohibited items with small size, and establish an automatic detection model based on feature fusion single shot multibox detector (FSSD) architecture. Two modifications are carried out to improve the detection accuracy. Firstly, the semantic enrichment module (SEM) with dilated convolution is applied to extract the low level feature with strong semantic information. Secondly, a residual module (Res) with residual blocks is added in the multibox detection architecture in order to extract more adequate features for target detection. The simulation results have demonstrated a better performance of the proposed detection model for prohibited items with small size compared with the state-of-the-arts.
doi_str_mv	10.1007/s11801-020-9118-x
format	Article
fullrecord	<record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2422415715</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2422415715</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-460d3742f662cbf006e8612b1b16cd30acc33454389abf52bc9b3c7cb6d9b2de3</originalsourceid><addsrcrecordid>eNp1UMFKAzEUDKJgqf0AbwHP0bxkN7s5lqJVKHhR8BaSbLZN6e7WJMXWrzdlBU--w3tzmJk3DEK3QO-B0uohAtQUCGWUyAzJ8QJNQEpOSgr8MmNRcQKSltdoFuOW5uGsqgs5Qcv5IQ2dTt7ixiVnkx96PLR4H4aNNz65BufVRfzl0wbHTu92OPpvh32PP0jQJ-w7vXbxBl21ehfd7PdO0fvT49vimaxely-L-YpYDiKRQtCGVwVrhWDWtJQKVwtgBgwI23CqreW8KAteS23akhkrDbeVNaKRhjWOT9Hd6JsDfh5cTGo7HEKfXypWMFZAWUGZWTCybBhiDK5V-5BzhpMCqs6VqbEylStT58rUMWvYqImZ269d-HP-X_QDcsxuWA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2422415715</pqid></control><display><type>article</type><title>Automatic detection of prohibited items with small size in X-ray images</title><source>SpringerLink Journals (MCLS)</source><source>Alma/SFX Local Collection</source><creator>Zhang, Yu-tao ; Zhang, Hai-gang ; Zhao, Teng-fei ; Yang, Jin-feng</creator><creatorcontrib>Zhang, Yu-tao ; Zhang, Hai-gang ; Zhao, Teng-fei ; Yang, Jin-feng</creatorcontrib><description>In this paper, we focus on the detection of prohibited items with small size, and establish an automatic detection model based on feature fusion single shot multibox detector (FSSD) architecture. Two modifications are carried out to improve the detection accuracy. Firstly, the semantic enrichment module (SEM) with dilated convolution is applied to extract the low level feature with strong semantic information. Secondly, a residual module (Res) with residual blocks is added in the multibox detection architecture in order to extract more adequate features for target detection. The simulation results have demonstrated a better performance of the proposed detection model for prohibited items with small size compared with the state-of-the-arts.</description><identifier>ISSN: 1673-1905</identifier><identifier>EISSN: 1993-5013</identifier><identifier>DOI: 10.1007/s11801-020-9118-x</identifier><language>eng</language><publisher>Tianjin: Tianjin University of Technology</publisher><subject>Architecture ; Computer simulation ; Convolution ; Feature extraction ; Image detection ; Lasers ; Low level ; Modules ; Optical Devices ; Optics ; Photonics ; Physics ; Physics and Astronomy ; Semantics ; Target detection</subject><ispartof>Optoelectronics letters, 2020-07, Vol.16 (4), p.313-317</ispartof><rights>Tianjin University of Technology and Springer-Verlag GmbH Germany, part of Springer Nature 2020</rights><rights>Tianjin University of Technology and Springer-Verlag GmbH Germany, part of Springer Nature 2020.</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-460d3742f662cbf006e8612b1b16cd30acc33454389abf52bc9b3c7cb6d9b2de3</citedby><cites>FETCH-LOGICAL-c316t-460d3742f662cbf006e8612b1b16cd30acc33454389abf52bc9b3c7cb6d9b2de3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11801-020-9118-x$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11801-020-9118-x$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Zhang, Yu-tao</creatorcontrib><creatorcontrib>Zhang, Hai-gang</creatorcontrib><creatorcontrib>Zhao, Teng-fei</creatorcontrib><creatorcontrib>Yang, Jin-feng</creatorcontrib><title>Automatic detection of prohibited items with small size in X-ray images</title><title>Optoelectronics letters</title><addtitle>Optoelectron. Lett</addtitle><description>In this paper, we focus on the detection of prohibited items with small size, and establish an automatic detection model based on feature fusion single shot multibox detector (FSSD) architecture. Two modifications are carried out to improve the detection accuracy. Firstly, the semantic enrichment module (SEM) with dilated convolution is applied to extract the low level feature with strong semantic information. Secondly, a residual module (Res) with residual blocks is added in the multibox detection architecture in order to extract more adequate features for target detection. The simulation results have demonstrated a better performance of the proposed detection model for prohibited items with small size compared with the state-of-the-arts.</description><subject>Architecture</subject><subject>Computer simulation</subject><subject>Convolution</subject><subject>Feature extraction</subject><subject>Image detection</subject><subject>Lasers</subject><subject>Low level</subject><subject>Modules</subject><subject>Optical Devices</subject><subject>Optics</subject><subject>Photonics</subject><subject>Physics</subject><subject>Physics and Astronomy</subject><subject>Semantics</subject><subject>Target detection</subject><issn>1673-1905</issn><issn>1993-5013</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp1UMFKAzEUDKJgqf0AbwHP0bxkN7s5lqJVKHhR8BaSbLZN6e7WJMXWrzdlBU--w3tzmJk3DEK3QO-B0uohAtQUCGWUyAzJ8QJNQEpOSgr8MmNRcQKSltdoFuOW5uGsqgs5Qcv5IQ2dTt7ixiVnkx96PLR4H4aNNz65BufVRfzl0wbHTu92OPpvh32PP0jQJ-w7vXbxBl21ehfd7PdO0fvT49vimaxely-L-YpYDiKRQtCGVwVrhWDWtJQKVwtgBgwI23CqreW8KAteS23akhkrDbeVNaKRhjWOT9Hd6JsDfh5cTGo7HEKfXypWMFZAWUGZWTCybBhiDK5V-5BzhpMCqs6VqbEylStT58rUMWvYqImZ269d-HP-X_QDcsxuWA</recordid><startdate>20200701</startdate><enddate>20200701</enddate><creator>Zhang, Yu-tao</creator><creator>Zhang, Hai-gang</creator><creator>Zhao, Teng-fei</creator><creator>Yang, Jin-feng</creator><general>Tianjin University of Technology</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20200701</creationdate><title>Automatic detection of prohibited items with small size in X-ray images</title><author>Zhang, Yu-tao ; Zhang, Hai-gang ; Zhao, Teng-fei ; Yang, Jin-feng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-460d3742f662cbf006e8612b1b16cd30acc33454389abf52bc9b3c7cb6d9b2de3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Architecture</topic><topic>Computer simulation</topic><topic>Convolution</topic><topic>Feature extraction</topic><topic>Image detection</topic><topic>Lasers</topic><topic>Low level</topic><topic>Modules</topic><topic>Optical Devices</topic><topic>Optics</topic><topic>Photonics</topic><topic>Physics</topic><topic>Physics and Astronomy</topic><topic>Semantics</topic><topic>Target detection</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Yu-tao</creatorcontrib><creatorcontrib>Zhang, Hai-gang</creatorcontrib><creatorcontrib>Zhao, Teng-fei</creatorcontrib><creatorcontrib>Yang, Jin-feng</creatorcontrib><collection>CrossRef</collection><jtitle>Optoelectronics letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Yu-tao</au><au>Zhang, Hai-gang</au><au>Zhao, Teng-fei</au><au>Yang, Jin-feng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automatic detection of prohibited items with small size in X-ray images</atitle><jtitle>Optoelectronics letters</jtitle><stitle>Optoelectron. Lett</stitle><date>2020-07-01</date><risdate>2020</risdate><volume>16</volume><issue>4</issue><spage>313</spage><epage>317</epage><pages>313-317</pages><issn>1673-1905</issn><eissn>1993-5013</eissn><abstract>In this paper, we focus on the detection of prohibited items with small size, and establish an automatic detection model based on feature fusion single shot multibox detector (FSSD) architecture. Two modifications are carried out to improve the detection accuracy. Firstly, the semantic enrichment module (SEM) with dilated convolution is applied to extract the low level feature with strong semantic information. Secondly, a residual module (Res) with residual blocks is added in the multibox detection architecture in order to extract more adequate features for target detection. The simulation results have demonstrated a better performance of the proposed detection model for prohibited items with small size compared with the state-of-the-arts.</abstract><cop>Tianjin</cop><pub>Tianjin University of Technology</pub><doi>10.1007/s11801-020-9118-x</doi><tpages>5</tpages></addata></record>
fulltext	fulltext
identifier	ISSN: 1673-1905
ispartof	Optoelectronics letters, 2020-07, Vol.16 (4), p.313-317
issn	1673-1905 1993-5013
language	eng
recordid	cdi_proquest_journals_2422415715
source	SpringerLink Journals (MCLS); Alma/SFX Local Collection
subjects	Architecture Computer simulation Convolution Feature extraction Image detection Lasers Low level Modules Optical Devices Optics Photonics Physics Physics and Astronomy Semantics Target detection
title	Automatic detection of prohibited items with small size in X-ray images
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T08%3A07%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automatic%20detection%20of%20prohibited%20items%20with%20small%20size%20in%20X-ray%20images&rft.jtitle=Optoelectronics%20letters&rft.au=Zhang,%20Yu-tao&rft.date=2020-07-01&rft.volume=16&rft.issue=4&rft.spage=313&rft.epage=317&rft.pages=313-317&rft.issn=1673-1905&rft.eissn=1993-5013&rft_id=info:doi/10.1007/s11801-020-9118-x&rft_dat=%3Cproquest_cross%3E2422415715%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2422415715&rft_id=info:pmid/&rfr_iscdi=true