Multisensor X-ray inspection of internal defects in horticultural products

•Internal quality inspection based on 3D-sensing and X-ray radiographs is proposed.•The performance of internal quality inspection of agrofood products is assessed.•Two datasets with defects of varying size and density were used for validation.•Radiographs with classic methods and a human operator w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Postharvest biology and technology 2017-06, Vol.128, p.33-43
Hauptverfasser: van Dael, M., Verboven, P., Dhaene, J., Van Hoorebeke, L., Sijbers, J., Nicolai, B.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 43
container_issue
container_start_page 33
container_title Postharvest biology and technology
container_volume 128
creator van Dael, M.
Verboven, P.
Dhaene, J.
Van Hoorebeke, L.
Sijbers, J.
Nicolai, B.
description •Internal quality inspection based on 3D-sensing and X-ray radiographs is proposed.•The performance of internal quality inspection of agrofood products is assessed.•Two datasets with defects of varying size and density were used for validation.•Radiographs with classic methods and a human operator were used as reference.•Proposed method outperforms reference methods, especially for small defects. A combination of 3-D vision and X-ray radiography is proposed to enable low-cost, generally applicable online inspection of internal quality of horticultural and potentially other products. The underlying concept assumes that the shape of the product is known beforehand through a deformable shape model. A 3-D vision system is used in combination with the shape model to accurately determine the complete outer surface shape of the sample. This shape is voxelized to generate a reference product from which a X-ray radiograph is simulated to be compared with a measured radiograph, hence revealing the presence of any defects or disorders. Advantages of this method are that small deviations in internal density are detected easily since the cumulative information of the bulk object shape is removed. Furthermore, no specific detection algorithms have to be developed for different types of defects, since the method will directly identify deviations from the ideal. Validation on two datasets and comparison with two reference detections methods (classical image processing and a human operator) shows that the proposed method reliably (accuracy >99%) detect defects larger than 3.5mm radius with densities differences between sample and defects as small as 10%. Voids are reliably (accuracy >99%) detected down to a radius of 1.5mm, corresponding to a volume of less than 0.02cm3.
doi_str_mv 10.1016/j.postharvbio.2017.02.002
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_1947845459</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0925521416304690</els_id><sourcerecordid>1947845459</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-e503b47e5532257ccedf3e631b5853d33b92eec3d4441b0dacaf123b21ee6e2e3</originalsourceid><addsrcrecordid>eNqNkMlOwzAQhi0EEqXwDkGcE8ZbliOqWFXEBSRuluNMVEclDrZTqW-Pq3LgyGk0888_y0fINYWCAi1vh2JyIW6037XWFQxoVQArANgJWdC64jnjsjwlC2iYzCWj4pxchDAAgJSyXpCX13kbbcAxOJ995l7vMzuGCU20bsxcn7KIftTbrMM-VUMqZBvnozXJOPskTN51c1IuyVmvtwGvfuOSfDzcv6-e8vXb4_Pqbp0bLpqYowTeigql5IzJyhjseo4lp62sJe84bxuGaHgnhKAtdNronjLeMopYIkO-JDfHuWnx94whqsHNhxODoo2oaiGFbFJXc-wy3oXgsVeTt1_a7xUFdUCnBvUHnTqgU8BUQpe8q6MX0xs7i14FY3FMl1qfGKjO2X9M-QGyvn9h</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1947845459</pqid></control><display><type>article</type><title>Multisensor X-ray inspection of internal defects in horticultural products</title><source>Elsevier ScienceDirect Journals Complete</source><creator>van Dael, M. ; Verboven, P. ; Dhaene, J. ; Van Hoorebeke, L. ; Sijbers, J. ; Nicolai, B.</creator><creatorcontrib>van Dael, M. ; Verboven, P. ; Dhaene, J. ; Van Hoorebeke, L. ; Sijbers, J. ; Nicolai, B.</creatorcontrib><description>•Internal quality inspection based on 3D-sensing and X-ray radiographs is proposed.•The performance of internal quality inspection of agrofood products is assessed.•Two datasets with defects of varying size and density were used for validation.•Radiographs with classic methods and a human operator were used as reference.•Proposed method outperforms reference methods, especially for small defects. A combination of 3-D vision and X-ray radiography is proposed to enable low-cost, generally applicable online inspection of internal quality of horticultural and potentially other products. The underlying concept assumes that the shape of the product is known beforehand through a deformable shape model. A 3-D vision system is used in combination with the shape model to accurately determine the complete outer surface shape of the sample. This shape is voxelized to generate a reference product from which a X-ray radiograph is simulated to be compared with a measured radiograph, hence revealing the presence of any defects or disorders. Advantages of this method are that small deviations in internal density are detected easily since the cumulative information of the bulk object shape is removed. Furthermore, no specific detection algorithms have to be developed for different types of defects, since the method will directly identify deviations from the ideal. Validation on two datasets and comparison with two reference detections methods (classical image processing and a human operator) shows that the proposed method reliably (accuracy &gt;99%) detect defects larger than 3.5mm radius with densities differences between sample and defects as small as 10%. Voids are reliably (accuracy &gt;99%) detected down to a radius of 1.5mm, corresponding to a volume of less than 0.02cm3.</description><identifier>ISSN: 0925-5214</identifier><identifier>EISSN: 1873-2356</identifier><identifier>DOI: 10.1016/j.postharvbio.2017.02.002</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Algorithms ; Bulk density ; Computer simulation ; Defects ; Deformation ; Formability ; Horticultural product ; Horticulture ; Image processing ; Inline ; Inspection ; Non-destructive ; Radiography ; Shape model ; Three dimensional models ; Vision systems ; X ray inspection ; X-ray ; X-ray radiography</subject><ispartof>Postharvest biology and technology, 2017-06, Vol.128, p.33-43</ispartof><rights>2017 Elsevier B.V.</rights><rights>Copyright Elsevier BV Jun 2017</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-e503b47e5532257ccedf3e631b5853d33b92eec3d4441b0dacaf123b21ee6e2e3</citedby><cites>FETCH-LOGICAL-c349t-e503b47e5532257ccedf3e631b5853d33b92eec3d4441b0dacaf123b21ee6e2e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.postharvbio.2017.02.002$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>van Dael, M.</creatorcontrib><creatorcontrib>Verboven, P.</creatorcontrib><creatorcontrib>Dhaene, J.</creatorcontrib><creatorcontrib>Van Hoorebeke, L.</creatorcontrib><creatorcontrib>Sijbers, J.</creatorcontrib><creatorcontrib>Nicolai, B.</creatorcontrib><title>Multisensor X-ray inspection of internal defects in horticultural products</title><title>Postharvest biology and technology</title><description>•Internal quality inspection based on 3D-sensing and X-ray radiographs is proposed.•The performance of internal quality inspection of agrofood products is assessed.•Two datasets with defects of varying size and density were used for validation.•Radiographs with classic methods and a human operator were used as reference.•Proposed method outperforms reference methods, especially for small defects. A combination of 3-D vision and X-ray radiography is proposed to enable low-cost, generally applicable online inspection of internal quality of horticultural and potentially other products. The underlying concept assumes that the shape of the product is known beforehand through a deformable shape model. A 3-D vision system is used in combination with the shape model to accurately determine the complete outer surface shape of the sample. This shape is voxelized to generate a reference product from which a X-ray radiograph is simulated to be compared with a measured radiograph, hence revealing the presence of any defects or disorders. Advantages of this method are that small deviations in internal density are detected easily since the cumulative information of the bulk object shape is removed. Furthermore, no specific detection algorithms have to be developed for different types of defects, since the method will directly identify deviations from the ideal. Validation on two datasets and comparison with two reference detections methods (classical image processing and a human operator) shows that the proposed method reliably (accuracy &gt;99%) detect defects larger than 3.5mm radius with densities differences between sample and defects as small as 10%. Voids are reliably (accuracy &gt;99%) detected down to a radius of 1.5mm, corresponding to a volume of less than 0.02cm3.</description><subject>Algorithms</subject><subject>Bulk density</subject><subject>Computer simulation</subject><subject>Defects</subject><subject>Deformation</subject><subject>Formability</subject><subject>Horticultural product</subject><subject>Horticulture</subject><subject>Image processing</subject><subject>Inline</subject><subject>Inspection</subject><subject>Non-destructive</subject><subject>Radiography</subject><subject>Shape model</subject><subject>Three dimensional models</subject><subject>Vision systems</subject><subject>X ray inspection</subject><subject>X-ray</subject><subject>X-ray radiography</subject><issn>0925-5214</issn><issn>1873-2356</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNqNkMlOwzAQhi0EEqXwDkGcE8ZbliOqWFXEBSRuluNMVEclDrZTqW-Pq3LgyGk0888_y0fINYWCAi1vh2JyIW6037XWFQxoVQArANgJWdC64jnjsjwlC2iYzCWj4pxchDAAgJSyXpCX13kbbcAxOJ995l7vMzuGCU20bsxcn7KIftTbrMM-VUMqZBvnozXJOPskTN51c1IuyVmvtwGvfuOSfDzcv6-e8vXb4_Pqbp0bLpqYowTeigql5IzJyhjseo4lp62sJe84bxuGaHgnhKAtdNronjLeMopYIkO-JDfHuWnx94whqsHNhxODoo2oaiGFbFJXc-wy3oXgsVeTt1_a7xUFdUCnBvUHnTqgU8BUQpe8q6MX0xs7i14FY3FMl1qfGKjO2X9M-QGyvn9h</recordid><startdate>201706</startdate><enddate>201706</enddate><creator>van Dael, M.</creator><creator>Verboven, P.</creator><creator>Dhaene, J.</creator><creator>Van Hoorebeke, L.</creator><creator>Sijbers, J.</creator><creator>Nicolai, B.</creator><general>Elsevier B.V</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QR</scope><scope>7SS</scope><scope>7T7</scope><scope>7U9</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>H94</scope><scope>P64</scope></search><sort><creationdate>201706</creationdate><title>Multisensor X-ray inspection of internal defects in horticultural products</title><author>van Dael, M. ; Verboven, P. ; Dhaene, J. ; Van Hoorebeke, L. ; Sijbers, J. ; Nicolai, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-e503b47e5532257ccedf3e631b5853d33b92eec3d4441b0dacaf123b21ee6e2e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Algorithms</topic><topic>Bulk density</topic><topic>Computer simulation</topic><topic>Defects</topic><topic>Deformation</topic><topic>Formability</topic><topic>Horticultural product</topic><topic>Horticulture</topic><topic>Image processing</topic><topic>Inline</topic><topic>Inspection</topic><topic>Non-destructive</topic><topic>Radiography</topic><topic>Shape model</topic><topic>Three dimensional models</topic><topic>Vision systems</topic><topic>X ray inspection</topic><topic>X-ray</topic><topic>X-ray radiography</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>van Dael, M.</creatorcontrib><creatorcontrib>Verboven, P.</creatorcontrib><creatorcontrib>Dhaene, J.</creatorcontrib><creatorcontrib>Van Hoorebeke, L.</creatorcontrib><creatorcontrib>Sijbers, J.</creatorcontrib><creatorcontrib>Nicolai, B.</creatorcontrib><collection>CrossRef</collection><collection>Chemoreception Abstracts</collection><collection>Entomology Abstracts (Full archive)</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Virology and AIDS Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Postharvest biology and technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>van Dael, M.</au><au>Verboven, P.</au><au>Dhaene, J.</au><au>Van Hoorebeke, L.</au><au>Sijbers, J.</au><au>Nicolai, B.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multisensor X-ray inspection of internal defects in horticultural products</atitle><jtitle>Postharvest biology and technology</jtitle><date>2017-06</date><risdate>2017</risdate><volume>128</volume><spage>33</spage><epage>43</epage><pages>33-43</pages><issn>0925-5214</issn><eissn>1873-2356</eissn><abstract>•Internal quality inspection based on 3D-sensing and X-ray radiographs is proposed.•The performance of internal quality inspection of agrofood products is assessed.•Two datasets with defects of varying size and density were used for validation.•Radiographs with classic methods and a human operator were used as reference.•Proposed method outperforms reference methods, especially for small defects. A combination of 3-D vision and X-ray radiography is proposed to enable low-cost, generally applicable online inspection of internal quality of horticultural and potentially other products. The underlying concept assumes that the shape of the product is known beforehand through a deformable shape model. A 3-D vision system is used in combination with the shape model to accurately determine the complete outer surface shape of the sample. This shape is voxelized to generate a reference product from which a X-ray radiograph is simulated to be compared with a measured radiograph, hence revealing the presence of any defects or disorders. Advantages of this method are that small deviations in internal density are detected easily since the cumulative information of the bulk object shape is removed. Furthermore, no specific detection algorithms have to be developed for different types of defects, since the method will directly identify deviations from the ideal. Validation on two datasets and comparison with two reference detections methods (classical image processing and a human operator) shows that the proposed method reliably (accuracy &gt;99%) detect defects larger than 3.5mm radius with densities differences between sample and defects as small as 10%. Voids are reliably (accuracy &gt;99%) detected down to a radius of 1.5mm, corresponding to a volume of less than 0.02cm3.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.postharvbio.2017.02.002</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0925-5214
ispartof Postharvest biology and technology, 2017-06, Vol.128, p.33-43
issn 0925-5214
1873-2356
language eng
recordid cdi_proquest_journals_1947845459
source Elsevier ScienceDirect Journals Complete
subjects Algorithms
Bulk density
Computer simulation
Defects
Deformation
Formability
Horticultural product
Horticulture
Image processing
Inline
Inspection
Non-destructive
Radiography
Shape model
Three dimensional models
Vision systems
X ray inspection
X-ray
X-ray radiography
title Multisensor X-ray inspection of internal defects in horticultural products
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T19%3A32%3A44IST&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=Multisensor%20X-ray%20inspection%20of%20internal%20defects%20in%20horticultural%20products&rft.jtitle=Postharvest%20biology%20and%20technology&rft.au=van%20Dael,%20M.&rft.date=2017-06&rft.volume=128&rft.spage=33&rft.epage=43&rft.pages=33-43&rft.issn=0925-5214&rft.eissn=1873-2356&rft_id=info:doi/10.1016/j.postharvbio.2017.02.002&rft_dat=%3Cproquest_cross%3E1947845459%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=1947845459&rft_id=info:pmid/&rft_els_id=S0925521416304690&rfr_iscdi=true