{"id":{"repo_id":"guelph","oai_identifier":"oai:atrium.lib.uoguelph.ca:10214/28112"},"canonical_url":"https://search.dev.ndltd.org/etd/guelph/oai:atrium.lib.uoguelph.ca:10214/28112","repository":{"repo_id":"guelph","name":"University of Guelph","base_url":"https://atrium.lib.uoguelph.ca/server/oai/request"},"display":{"title":"Classifying Canadian Pork Primals Based on Colour, Firmness, and Lean-fat-bone Ratio","abstract":"The work aimed to provide innovations for categorizing Canadian pork primals, including loins, hams, and bellies, by focusing on essential quality attributes: colour, lean-to-fat ratio, and firmness, ultimately enhancing industrial processes. Study 1 compared recently developed devices to Minolta spectrophotometers for measuring colour (252 loin chops; 46 tenderloins). Newly developed instruments presented low RSD (< 5%), with minor variations in the a* values for the Nix Pro II and b* values for the Spectro 1 Pro. Correlations with subjective standards were higher for Nix and Spectro devices, compared to Minolta. Newly developed devices presented reliable pork surface colour measurement. Study 2 investigated the image analysis method to categorize pale pork loins. Colour of the ventral side (n= 550) was correlated (r= 0.79, P< 0.05) to the lean muscle area of centre chop. Thresholds at multiple levels (2.5th, 5th, and 7.5th) for the palest ventral surfaces were selected to classify centre chop. The method achieved a categorization accuracy of 87% at the 7.5th percentile of ventral sides, suggesting its potential utility for processors in the pre-sorting of commercial pork. Study 3 used image analysis on 248 bone-in hams to classify extremely fat or lean hams. Linear measurements of fat layers predicted known composition of the whole ham with R2= 0.7. A system based on these predictions aimed to classify extremely fat or lean hams at the 10th percentile threshold. Accuracy dropped by 18% for lean ham prediction but increased by 60% for fat ham prediction at the 30th percentile threshold. In Study 4, an automated conveyor system simulated the production line movement to classify 94 bellies based on firmness at 4°C, 2°C, and -1.5°C. Temperature significantly (P< 0.05) affected bending angles. Multiple bends only changed firmness classification at 4°C and 2°C. The findings from all studies contribute insights for the development of an automated classification system focusing on meat surface colour or the firmness of pork belly primals. Furthermore, the linear measurements on ham faces can be effectively utilized in the construction of a manual device designed for the classification of pork ham primals based on composition.","abstract_html":"The work aimed to provide innovations for categorizing Canadian pork primals, including loins, hams, and bellies, by focusing on essential quality attributes: colour, lean-to-fat ratio, and firmness, ultimately enhancing industrial processes. Study 1 compared recently developed devices to Minolta spectrophotometers for measuring colour (252 loin chops; 46 tenderloins). Newly developed instruments presented low RSD (&lt; 5%), with minor variations in the a* values for the Nix Pro II and b* values for the Spectro 1 Pro. Correlations with subjective standards were higher for Nix and Spectro devices, compared to Minolta. Newly developed devices presented reliable pork surface colour measurement. Study 2 investigated the image analysis method to categorize pale pork loins. Colour of the ventral side (n= 550) was correlated (r= 0.79, P&lt; 0.05) to the lean muscle area of centre chop. Thresholds at multiple levels (2.5th, 5th, and 7.5th) for the palest ventral surfaces were selected to classify centre chop. The method achieved a categorization accuracy of 87% at the 7.5th percentile of ventral sides, suggesting its potential utility for processors in the pre-sorting of commercial pork. Study 3 used image analysis on 248 bone-in hams to classify extremely fat or lean hams. Linear measurements of fat layers predicted known composition of the whole ham with R2= 0.7. A system based on these predictions aimed to classify extremely fat or lean hams at the 10th percentile threshold. Accuracy dropped by 18% for lean ham prediction but increased by 60% for fat ham prediction at the 30th percentile threshold. In Study 4, an automated conveyor system simulated the production line movement to classify 94 bellies based on firmness at 4°C, 2°C, and -1.5°C. Temperature significantly (P&lt; 0.05) affected bending angles. Multiple bends only changed firmness classification at 4°C and 2°C. The findings from all studies contribute insights for the development of an automated classification system focusing on meat surface colour or the firmness of pork belly primals. Furthermore, the linear measurements on ham faces can be effectively utilized in the construction of a manual device designed for the classification of pork ham primals based on composition.","abstract_has_math":false,"creators":["Wei, Xinyi"],"institution":"University of Guelph","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Duizer, Lisa","Manuel, Juárez","Bohrer, Benjamin","Annamalai, Manickavasagan"],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-08-21T16:45:07Z","subjects":["pork","classification","quality","colour","firmness","lean-fat-bone"],"languages":["en"],"rights":["Attribution-NoDerivatives 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10214/28112","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"source_record":{"url":"https://atrium.lib.uoguelph.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aatrium.lib.uoguelph.ca%3A10214%2F28112","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Duizer, Lisa","Manuel, Juárez","Bohrer, Benjamin","Annamalai, Manickavasagan"]},{"key":"dc:creator","label":"Author","values":["Wei, Xinyi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-01-15T15:59:40Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-01-15T15:59:40Z"]},{"key":"dc:publisher","label":"Institution","values":["University of Guelph"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["pork","classification","quality","colour","firmness","lean-fat-bone"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NoDerivatives 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10214/28112"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The work aimed to provide innovations for categorizing Canadian pork primals, including loins, hams, and bellies, by focusing on essential quality attributes: colour, lean-to-fat ratio, and firmness, ultimately enhancing industrial processes. Study 1 compared recently developed devices to Minolta spectrophotometers for measuring colour (252 loin chops; 46 tenderloins). Newly developed instruments presented low RSD (< 5%), with minor variations in the a* values for the Nix Pro II and b* values for the Spectro 1 Pro. Correlations with subjective standards were higher for Nix and Spectro devices, compared to Minolta. Newly developed devices presented reliable pork surface colour measurement. Study 2 investigated the image analysis method to categorize pale pork loins. Colour of the ventral side (n= 550) was correlated (r= 0.79, P< 0.05) to the lean muscle area of centre chop. Thresholds at multiple levels (2.5th, 5th, and 7.5th) for the palest ventral surfaces were selected to classify centre chop. The method achieved a categorization accuracy of 87% at the 7.5th percentile of ventral sides, suggesting its potential utility for processors in the pre-sorting of commercial pork. Study 3 used image analysis on 248 bone-in hams to classify extremely fat or lean hams. Linear measurements of fat layers predicted known composition of the whole ham with R2= 0.7. A system based on these predictions aimed to classify extremely fat or lean hams at the 10th percentile threshold. Accuracy dropped by 18% for lean ham prediction but increased by 60% for fat ham prediction at the 30th percentile threshold. In Study 4, an automated conveyor system simulated the production line movement to classify 94 bellies based on firmness at 4°C, 2°C, and -1.5°C. Temperature significantly (P< 0.05) affected bending angles. Multiple bends only changed firmness classification at 4°C and 2°C. The findings from all studies contribute insights for the development of an automated classification system focusing on meat surface colour or the firmness of pork belly primals. Furthermore, the linear measurements on ham faces can be effectively utilized in the construction of a manual device designed for the classification of pork ham primals based on composition."]},{"key":"dc:title","label":"Title","values":["Classifying Canadian Pork Primals Based on Colour, Firmness, and Lean-fat-bone Ratio"]}]}],"canonical_facts":{"dc:contributor.advisor":["Duizer, Lisa","Manuel, Juárez","Bohrer, Benjamin","Annamalai, Manickavasagan"],"dc:creator":["Wei, Xinyi"],"dc:date.accessioned":["2024-01-15T15:59:40Z"],"dc:date.available":["2024-01-15T15:59:40Z"],"dc:description.abstract":["The work aimed to provide innovations for categorizing Canadian pork primals, including loins, hams, and bellies, by focusing on essential quality attributes: colour, lean-to-fat ratio, and firmness, ultimately enhancing industrial processes. Study 1 compared recently developed devices to Minolta spectrophotometers for measuring colour (252 loin chops; 46 tenderloins). Newly developed instruments presented low RSD (< 5%), with minor variations in the a* values for the Nix Pro II and b* values for the Spectro 1 Pro. Correlations with subjective standards were higher for Nix and Spectro devices, compared to Minolta. Newly developed devices presented reliable pork surface colour measurement. Study 2 investigated the image analysis method to categorize pale pork loins. Colour of the ventral side (n= 550) was correlated (r= 0.79, P< 0.05) to the lean muscle area of centre chop. Thresholds at multiple levels (2.5th, 5th, and 7.5th) for the palest ventral surfaces were selected to classify centre chop. The method achieved a categorization accuracy of 87% at the 7.5th percentile of ventral sides, suggesting its potential utility for processors in the pre-sorting of commercial pork. Study 3 used image analysis on 248 bone-in hams to classify extremely fat or lean hams. Linear measurements of fat layers predicted known composition of the whole ham with R2= 0.7. A system based on these predictions aimed to classify extremely fat or lean hams at the 10th percentile threshold. Accuracy dropped by 18% for lean ham prediction but increased by 60% for fat ham prediction at the 30th percentile threshold. In Study 4, an automated conveyor system simulated the production line movement to classify 94 bellies based on firmness at 4°C, 2°C, and -1.5°C. Temperature significantly (P< 0.05) affected bending angles. Multiple bends only changed firmness classification at 4°C and 2°C. The findings from all studies contribute insights for the development of an automated classification system focusing on meat surface colour or the firmness of pork belly primals. Furthermore, the linear measurements on ham faces can be effectively utilized in the construction of a manual device designed for the classification of pork ham primals based on composition."],"dc:identifier.uri":["https://hdl.handle.net/10214/28112"],"dc:language.iso":["en"],"dc:publisher":["University of Guelph"],"dc:rights":["Attribution-NoDerivatives 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by-nd/4.0/"],"dc:subject":["pork","classification","quality","colour","firmness","lean-fat-bone"],"dc:title":["Classifying Canadian Pork Primals Based on Colour, Firmness, and Lean-fat-bone Ratio"],"dc:type":["Thesis"]},"updated_at":"2026-08-21T16:45:07Z"}