Pork quality and marbling level assessment using a hyperspectral imaging system

Pork quality is usually evaluated subjectively based on color, texture and exudation characteristics of the meat. In this study, a hyperspectral imaging-based technique was evaluated for rapid, accurate and objective assessment of pork quality. In addition, marbling level was also automatically dete...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of food engineering 2007-11, Vol.83 (1), p.10-16
Hauptverfasser: Qiao, Jun, Ngadi, Michael O., Wang, Ning, Gariépy, Claude, Prasher, Shiv.O.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 16
container_issue 1
container_start_page 10
container_title Journal of food engineering
container_volume 83
creator Qiao, Jun
Ngadi, Michael O.
Wang, Ning
Gariépy, Claude
Prasher, Shiv.O.
description Pork quality is usually evaluated subjectively based on color, texture and exudation characteristics of the meat. In this study, a hyperspectral imaging-based technique was evaluated for rapid, accurate and objective assessment of pork quality. In addition, marbling level was also automatically determined. The system was able to extract spectral characteristics of pork samples. Appropriate spatial features were obtained for marbling distribution in pork meat. Existing marbling standards were scanned, and indices of the marbling scores were formulated by co-occurrence matrix. The principal component analysis (PCA) method was used to compress the entire spectral wavelengths (430–1000 nm) into 5, 10 and 20 principal components (PCs), which were then clustered into quality groups. Artificial neural network was used to classify these groups. Results showed that reddish, firm and non-exudative (RFN) and reddish, soft and exudative (RSE) samples were successfully grouped; the total corrected ratio was 75–80%. The feed-forward neural network model yielded corrected classification as 69% by 5 PCs and 85% by 10 PCs. Angular second moment was successfully used to determine marbling scores excepting the score at 10.0. Forty samples were sorted and the result showed that the samples’ marbling score ranged from 3.0 to 5.0.
doi_str_mv 10.1016/j.jfoodeng.2007.02.038
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_896243675</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0260877407001185</els_id><sourcerecordid>896243675</sourcerecordid><originalsourceid>FETCH-LOGICAL-c398t-6d30501977b30d172c02380b42b57276e7a065029f1c952e955b250a3f2274e03</originalsourceid><addsrcrecordid>eNqFkE1r3DAQhk1podskf6H1pfRkdzSyLPnWEvoFgQSanIUsj7fayvZG4w3sv6-WTemxcxkYnpl5eYrirYBagGg_7urduCwDzdsaAXQNWIM0L4qNMFpWSmt4WWwAW6iM1s3r4g3zDgAUIG6K27sl_S4fDy6G9Vi6eSgnl_oY5m0Z6Yli6ZiJeaJ5LQ98Grvy13FPiffk1-RiGSa3Pc35yCtNl8Wr0UWmq-d-UTx8_XJ__b26uf324_rzTeVlZ9aqHWQOIDqtewmD0OgBpYG-wV5p1C1pB21O2I3CdwqpU6pHBU6OiLohkBfFh_PdfVoeD8SrnQJ7itHNtBzYmq7FRrZaZbI9kz4tzIlGu085czpaAfYk0O7sX4H2JNAC2iwwL75_fuHYuzgmN_vA_7ZNLoGYuXdnbnSLdduUmYefCELmW0ZJ02Ti05mgbOQpULLsA82ehpCyRTss4X9h_gA1k5JZ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>896243675</pqid></control><display><type>article</type><title>Pork quality and marbling level assessment using a hyperspectral imaging system</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Qiao, Jun ; Ngadi, Michael O. ; Wang, Ning ; Gariépy, Claude ; Prasher, Shiv.O.</creator><creatorcontrib>Qiao, Jun ; Ngadi, Michael O. ; Wang, Ning ; Gariépy, Claude ; Prasher, Shiv.O.</creatorcontrib><description>Pork quality is usually evaluated subjectively based on color, texture and exudation characteristics of the meat. In this study, a hyperspectral imaging-based technique was evaluated for rapid, accurate and objective assessment of pork quality. In addition, marbling level was also automatically determined. The system was able to extract spectral characteristics of pork samples. Appropriate spatial features were obtained for marbling distribution in pork meat. Existing marbling standards were scanned, and indices of the marbling scores were formulated by co-occurrence matrix. The principal component analysis (PCA) method was used to compress the entire spectral wavelengths (430–1000 nm) into 5, 10 and 20 principal components (PCs), which were then clustered into quality groups. Artificial neural network was used to classify these groups. Results showed that reddish, firm and non-exudative (RFN) and reddish, soft and exudative (RSE) samples were successfully grouped; the total corrected ratio was 75–80%. The feed-forward neural network model yielded corrected classification as 69% by 5 PCs and 85% by 10 PCs. Angular second moment was successfully used to determine marbling scores excepting the score at 10.0. Forty samples were sorted and the result showed that the samples’ marbling score ranged from 3.0 to 5.0.</description><identifier>ISSN: 0260-8774</identifier><identifier>EISSN: 1873-5770</identifier><identifier>DOI: 10.1016/j.jfoodeng.2007.02.038</identifier><identifier>CODEN: JFOEDH</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Assessments ; Biological and medical sciences ; Classification ; Cluster analysis ; color ; Exudation ; Food engineering ; Food industries ; Fundamental and applied biological sciences. Psychology ; General aspects ; hyperspectral imagery ; Hyperspectral imaging ; image analysis ; Marbling ; Meat ; Meat and meat product industries ; meat quality ; Neural network ; neural networks ; PCA ; Pork ; Pork quality ; principal component analysis ; rapid methods ; Spectra ; Texture</subject><ispartof>Journal of food engineering, 2007-11, Vol.83 (1), p.10-16</ispartof><rights>2007 Elsevier Ltd</rights><rights>2007 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c398t-6d30501977b30d172c02380b42b57276e7a065029f1c952e955b250a3f2274e03</citedby><cites>FETCH-LOGICAL-c398t-6d30501977b30d172c02380b42b57276e7a065029f1c952e955b250a3f2274e03</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.jfoodeng.2007.02.038$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>309,310,314,780,784,789,790,3550,23930,23931,25140,27924,27925,45995</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=18888122$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Qiao, Jun</creatorcontrib><creatorcontrib>Ngadi, Michael O.</creatorcontrib><creatorcontrib>Wang, Ning</creatorcontrib><creatorcontrib>Gariépy, Claude</creatorcontrib><creatorcontrib>Prasher, Shiv.O.</creatorcontrib><title>Pork quality and marbling level assessment using a hyperspectral imaging system</title><title>Journal of food engineering</title><description>Pork quality is usually evaluated subjectively based on color, texture and exudation characteristics of the meat. In this study, a hyperspectral imaging-based technique was evaluated for rapid, accurate and objective assessment of pork quality. In addition, marbling level was also automatically determined. The system was able to extract spectral characteristics of pork samples. Appropriate spatial features were obtained for marbling distribution in pork meat. Existing marbling standards were scanned, and indices of the marbling scores were formulated by co-occurrence matrix. The principal component analysis (PCA) method was used to compress the entire spectral wavelengths (430–1000 nm) into 5, 10 and 20 principal components (PCs), which were then clustered into quality groups. Artificial neural network was used to classify these groups. Results showed that reddish, firm and non-exudative (RFN) and reddish, soft and exudative (RSE) samples were successfully grouped; the total corrected ratio was 75–80%. The feed-forward neural network model yielded corrected classification as 69% by 5 PCs and 85% by 10 PCs. Angular second moment was successfully used to determine marbling scores excepting the score at 10.0. Forty samples were sorted and the result showed that the samples’ marbling score ranged from 3.0 to 5.0.</description><subject>Assessments</subject><subject>Biological and medical sciences</subject><subject>Classification</subject><subject>Cluster analysis</subject><subject>color</subject><subject>Exudation</subject><subject>Food engineering</subject><subject>Food industries</subject><subject>Fundamental and applied biological sciences. Psychology</subject><subject>General aspects</subject><subject>hyperspectral imagery</subject><subject>Hyperspectral imaging</subject><subject>image analysis</subject><subject>Marbling</subject><subject>Meat</subject><subject>Meat and meat product industries</subject><subject>meat quality</subject><subject>Neural network</subject><subject>neural networks</subject><subject>PCA</subject><subject>Pork</subject><subject>Pork quality</subject><subject>principal component analysis</subject><subject>rapid methods</subject><subject>Spectra</subject><subject>Texture</subject><issn>0260-8774</issn><issn>1873-5770</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2007</creationdate><recordtype>article</recordtype><recordid>eNqFkE1r3DAQhk1podskf6H1pfRkdzSyLPnWEvoFgQSanIUsj7fayvZG4w3sv6-WTemxcxkYnpl5eYrirYBagGg_7urduCwDzdsaAXQNWIM0L4qNMFpWSmt4WWwAW6iM1s3r4g3zDgAUIG6K27sl_S4fDy6G9Vi6eSgnl_oY5m0Z6Yli6ZiJeaJ5LQ98Grvy13FPiffk1-RiGSa3Pc35yCtNl8Wr0UWmq-d-UTx8_XJ__b26uf324_rzTeVlZ9aqHWQOIDqtewmD0OgBpYG-wV5p1C1pB21O2I3CdwqpU6pHBU6OiLohkBfFh_PdfVoeD8SrnQJ7itHNtBzYmq7FRrZaZbI9kz4tzIlGu085czpaAfYk0O7sX4H2JNAC2iwwL75_fuHYuzgmN_vA_7ZNLoGYuXdnbnSLdduUmYefCELmW0ZJ02Ti05mgbOQpULLsA82ehpCyRTss4X9h_gA1k5JZ</recordid><startdate>20071101</startdate><enddate>20071101</enddate><creator>Qiao, Jun</creator><creator>Ngadi, Michael O.</creator><creator>Wang, Ning</creator><creator>Gariépy, Claude</creator><creator>Prasher, Shiv.O.</creator><general>Elsevier Ltd</general><general>Elsevier</general><scope>FBQ</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20071101</creationdate><title>Pork quality and marbling level assessment using a hyperspectral imaging system</title><author>Qiao, Jun ; Ngadi, Michael O. ; Wang, Ning ; Gariépy, Claude ; Prasher, Shiv.O.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c398t-6d30501977b30d172c02380b42b57276e7a065029f1c952e955b250a3f2274e03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Assessments</topic><topic>Biological and medical sciences</topic><topic>Classification</topic><topic>Cluster analysis</topic><topic>color</topic><topic>Exudation</topic><topic>Food engineering</topic><topic>Food industries</topic><topic>Fundamental and applied biological sciences. Psychology</topic><topic>General aspects</topic><topic>hyperspectral imagery</topic><topic>Hyperspectral imaging</topic><topic>image analysis</topic><topic>Marbling</topic><topic>Meat</topic><topic>Meat and meat product industries</topic><topic>meat quality</topic><topic>Neural network</topic><topic>neural networks</topic><topic>PCA</topic><topic>Pork</topic><topic>Pork quality</topic><topic>principal component analysis</topic><topic>rapid methods</topic><topic>Spectra</topic><topic>Texture</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Qiao, Jun</creatorcontrib><creatorcontrib>Ngadi, Michael O.</creatorcontrib><creatorcontrib>Wang, Ning</creatorcontrib><creatorcontrib>Gariépy, Claude</creatorcontrib><creatorcontrib>Prasher, Shiv.O.</creatorcontrib><collection>AGRIS</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><jtitle>Journal of food engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Qiao, Jun</au><au>Ngadi, Michael O.</au><au>Wang, Ning</au><au>Gariépy, Claude</au><au>Prasher, Shiv.O.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Pork quality and marbling level assessment using a hyperspectral imaging system</atitle><jtitle>Journal of food engineering</jtitle><date>2007-11-01</date><risdate>2007</risdate><volume>83</volume><issue>1</issue><spage>10</spage><epage>16</epage><pages>10-16</pages><issn>0260-8774</issn><eissn>1873-5770</eissn><coden>JFOEDH</coden><abstract>Pork quality is usually evaluated subjectively based on color, texture and exudation characteristics of the meat. In this study, a hyperspectral imaging-based technique was evaluated for rapid, accurate and objective assessment of pork quality. In addition, marbling level was also automatically determined. The system was able to extract spectral characteristics of pork samples. Appropriate spatial features were obtained for marbling distribution in pork meat. Existing marbling standards were scanned, and indices of the marbling scores were formulated by co-occurrence matrix. The principal component analysis (PCA) method was used to compress the entire spectral wavelengths (430–1000 nm) into 5, 10 and 20 principal components (PCs), which were then clustered into quality groups. Artificial neural network was used to classify these groups. Results showed that reddish, firm and non-exudative (RFN) and reddish, soft and exudative (RSE) samples were successfully grouped; the total corrected ratio was 75–80%. The feed-forward neural network model yielded corrected classification as 69% by 5 PCs and 85% by 10 PCs. Angular second moment was successfully used to determine marbling scores excepting the score at 10.0. Forty samples were sorted and the result showed that the samples’ marbling score ranged from 3.0 to 5.0.</abstract><cop>Oxford</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.jfoodeng.2007.02.038</doi><tpages>7</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0260-8774
ispartof Journal of food engineering, 2007-11, Vol.83 (1), p.10-16
issn 0260-8774
1873-5770
language eng
recordid cdi_proquest_miscellaneous_896243675
source Elsevier ScienceDirect Journals Complete
subjects Assessments
Biological and medical sciences
Classification
Cluster analysis
color
Exudation
Food engineering
Food industries
Fundamental and applied biological sciences. Psychology
General aspects
hyperspectral imagery
Hyperspectral imaging
image analysis
Marbling
Meat
Meat and meat product industries
meat quality
Neural network
neural networks
PCA
Pork
Pork quality
principal component analysis
rapid methods
Spectra
Texture
title Pork quality and marbling level assessment using a hyperspectral imaging system
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T10%3A10%3A40IST&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=Pork%20quality%20and%20marbling%20level%20assessment%20using%20a%20hyperspectral%20imaging%20system&rft.jtitle=Journal%20of%20food%20engineering&rft.au=Qiao,%20Jun&rft.date=2007-11-01&rft.volume=83&rft.issue=1&rft.spage=10&rft.epage=16&rft.pages=10-16&rft.issn=0260-8774&rft.eissn=1873-5770&rft.coden=JFOEDH&rft_id=info:doi/10.1016/j.jfoodeng.2007.02.038&rft_dat=%3Cproquest_cross%3E896243675%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=896243675&rft_id=info:pmid/&rft_els_id=S0260877407001185&rfr_iscdi=true