{"id":{"repo_id":"colostate","oai_identifier":"oai:mountainscholar.org:10217/47436"},"canonical_url":"https://search.dev.ndltd.org/etd/colostate/oai:mountainscholar.org:10217/47436","repository":{"repo_id":"colostate","name":"Colorado State University","base_url":"https://api.mountainscholar.org/server/oai/request"},"display":{"title":"Prediction of primal and subprimal beef yields with video image analysis","abstract":"An ability to segregate carcasses based on both primal and subprimal yields would further facilitate value-based marketing in the beef industry. This study was conducted to evaluate Video Image Analysis (VIA) output to predict fabricated primal and subprimal yields. Carcasses were selected based on yield grade (YG 1, YG 2, YG 3, YG 4, and YG 5) as well as hot carcass weight (< 341 kg and ≥ 341 kg). A yield dissection was performed and at each step in fabrication, recovered product weights for each carcass to remain in the study summed to ≥ 99 % of the starting chilled weight of each primal and subprimal. For yield predictions, VIA output from 12th/13th rib interface images from the VBG 2000 (single-component; n = 142, development; n = 58, validation), or from VBG 2000 output in combination with output from loin/round primal interface images from the VPS 2000 (dual-component; n = 129, development; n = 56, validation) were regressed on yields of fabricated primals and subprimals. Yield variables were predicted as a percent of the aggregate chilled carcass side weight. Results from prediction equations for primals or the largest subprimal representing a primal in the study, indicated moderate and low predictive capability for development and validation datasets, respectively. For the square cut chuck (IMPS 113), commodity iii trimmed brisket (IMPS120, PS0 1), ribeye (IMPS 112A, PSO 3, 5.1 cm x 5.1 cm lip-on), short plate (IMPS 121), loin primal (IMPS 172), flank primal, and round primal (IMPS 158) R2 / adjusted R2 values (development / validation) of 0.39 / 0.11, 0.16 / 0.05, 0.31 / 0.12, 0.40 / 0.03, 0.56 / 0.12, 0.35 / -.005, and 0.64 / -0.05, respectively, for single-component predictions and 0.60 / -0.13, 0.57 / -0.03, 0.40 / 0.08, 0.52 / -0.15, 0.66 / -3.42, 0.66 / -3.42, 0.47 / -0.004, and 0.73 / -0.10, respectively, for dual-component predictions was observed. The best performing single-component model was for the tenderloin (IMPS 189A) with R2 / adjusted R2 values (development / validation) of 0.42 / 0.50. The best performing dual component model was for the cap off inside round (IMPS 169A) with R2 values (development / validation) of 0.58 / 0.30. The ability of single-component and dual-component equations to predict yields of several primal and subprimal cuts, with reasonable accuracy and precision in the development dataset, yet low accuracy and precision in the validation dataset, suggests that the VIA systems tested in this study do not have the potential as tool for more sensitive carcass segregation at this time. Further investigation to reveal the full potential of dual-component primal and subprimal cut yield prediction, perhaps looking at a sample population with greater variance (i.e., equal number of yield grades for equation development) and having VPS 2000 images available from each primal surface to provide independent variables representative of the entire carcass, is justifiable.","abstract_html":"An ability to segregate carcasses based on both primal and subprimal yields would further facilitate value-based marketing in the beef industry. This study was conducted to evaluate Video Image Analysis (VIA) output to predict fabricated primal and subprimal yields. Carcasses were selected based on yield grade (YG 1, YG 2, YG 3, YG 4, and YG 5) as well as hot carcass weight (&lt; 341 kg and ≥ 341 kg). A yield dissection was performed and at each step in fabrication, recovered product weights for each carcass to remain in the study summed to ≥ 99 % of the starting chilled weight of each primal and subprimal. For yield predictions, VIA output from 12th/13th rib interface images from the VBG 2000 (single-component; n = 142, development; n = 58, validation), or from VBG 2000 output in combination with output from loin/round primal interface images from the VPS 2000 (dual-component; n = 129, development; n = 56, validation) were regressed on yields of fabricated primals and subprimals. Yield variables were predicted as a percent of the aggregate chilled carcass side weight. Results from prediction equations for primals or the largest subprimal representing a primal in the study, indicated moderate and low predictive capability for development and validation datasets, respectively. For the square cut chuck (IMPS 113), commodity iii trimmed brisket (IMPS120, PS0 1), ribeye (IMPS 112A, PSO 3, 5.1 cm x 5.1 cm lip-on), short plate (IMPS 121), loin primal (IMPS 172), flank primal, and round primal (IMPS 158) R2 / adjusted R2 values (development / validation) of 0.39 / 0.11, 0.16 / 0.05, 0.31 / 0.12, 0.40 / 0.03, 0.56 / 0.12, 0.35 / -.005, and 0.64 / -0.05, respectively, for single-component predictions and 0.60 / -0.13, 0.57 / -0.03, 0.40 / 0.08, 0.52 / -0.15, 0.66 / -3.42, 0.66 / -3.42, 0.47 / -0.004, and 0.73 / -0.10, respectively, for dual-component predictions was observed. The best performing single-component model was for the tenderloin (IMPS 189A) with R2 / adjusted R2 values (development / validation) of 0.42 / 0.50. The best performing dual component model was for the cap off inside round (IMPS 169A) with R2 values (development / validation) of 0.58 / 0.30. The ability of single-component and dual-component equations to predict yields of several primal and subprimal cuts, with reasonable accuracy and precision in the development dataset, yet low accuracy and precision in the validation dataset, suggests that the VIA systems tested in this study do not have the potential as tool for more sensitive carcass segregation at this time. Further investigation to reveal the full potential of dual-component primal and subprimal cut yield prediction, perhaps looking at a sample population with greater variance (i.e., equal number of yield grades for equation development) and having VPS 2000 images available from each primal surface to provide independent variables representative of the entire carcass, is justifiable.","abstract_has_math":false,"creators":["Nunes, Trevor Francis, author","Belk, Keith Evan, 1961-, advisor","Tatum, J. Daryl, committee member","Smith, Gary C., committee member","Chapman, Phillip L., committee member"],"institution":"Colorado State University. Libraries","degree_name":"Master of Science (M.S.)","degree_level":"Masters","degree_discipline":"Animal Sciences","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011","date_published":"2011","updated_at":"2026-07-27T19:13:14Z","subjects":["subprimal yield","primal yield","video image analysis","beef","cutability"],"languages":["eng","English"],"rights":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.25675/3.018759"],"render_values":[{"text":"https://doi.org/10.25675/3.018759","href":"https://doi.org/10.25675/3.018759","code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10217/47436","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Nunes, Trevor Francis, author","Belk, Keith Evan, 1961-, advisor","Tatum, J. Daryl, committee member","Smith, Gary C., committee member","Chapman, Phillip L., committee member"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2007-01-03T05:16:14Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2007-01-03T05:16:14Z"]},{"key":"dc:date.issued","label":"Date","values":["2011"]},{"key":"dc:publisher","label":"Institution","values":["Colorado State University. Libraries"]},{"key":"dc:type","label":"Dc Type","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Animal Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (M.S.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Colorado State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["subprimal yield","primal yield","video image analysis","beef","cutability"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["Nunes_colostate_0053N_10387.pdf"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10217/47436","https://doi.org/10.25675/3.018759"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["An ability to segregate carcasses based on both primal and subprimal yields would further facilitate value-based marketing in the beef industry. This study was conducted to evaluate Video Image Analysis (VIA) output to predict fabricated primal and subprimal yields. Carcasses were selected based on yield grade (YG 1, YG 2, YG 3, YG 4, and YG 5) as well as hot carcass weight (< 341 kg and ≥ 341 kg). A yield dissection was performed and at each step in fabrication, recovered product weights for each carcass to remain in the study summed to ≥ 99 % of the starting chilled weight of each primal and subprimal. For yield predictions, VIA output from 12th/13th rib interface images from the VBG 2000 (single-component; n = 142, development; n = 58, validation), or from VBG 2000 output in combination with output from loin/round primal interface images from the VPS 2000 (dual-component; n = 129, development; n = 56, validation) were regressed on yields of fabricated primals and subprimals. Yield variables were predicted as a percent of the aggregate chilled carcass side weight. Results from prediction equations for primals or the largest subprimal representing a primal in the study, indicated moderate and low predictive capability for development and validation datasets, respectively. For the square cut chuck (IMPS 113), commodity iii trimmed brisket (IMPS120, PS0 1), ribeye (IMPS 112A, PSO 3, 5.1 cm x 5.1 cm lip-on), short plate (IMPS 121), loin primal (IMPS 172), flank primal, and round primal (IMPS 158) R2 / adjusted R2 values (development / validation) of 0.39 / 0.11, 0.16 / 0.05, 0.31 / 0.12, 0.40 / 0.03, 0.56 / 0.12, 0.35 / -.005, and 0.64 / -0.05, respectively, for single-component predictions and 0.60 / -0.13, 0.57 / -0.03, 0.40 / 0.08, 0.52 / -0.15, 0.66 / -3.42, 0.66 / -3.42, 0.47 / -0.004, and 0.73 / -0.10, respectively, for dual-component predictions was observed. The best performing single-component model was for the tenderloin (IMPS 189A) with R2 / adjusted R2 values (development / validation) of 0.42 / 0.50. The best performing dual component model was for the cap off inside round (IMPS 169A) with R2 values (development / validation) of 0.58 / 0.30. The ability of single-component and dual-component equations to predict yields of several primal and subprimal cuts, with reasonable accuracy and precision in the development dataset, yet low accuracy and precision in the validation dataset, suggests that the VIA systems tested in this study do not have the potential as tool for more sensitive carcass segregation at this time. Further investigation to reveal the full potential of dual-component primal and subprimal cut yield prediction, perhaps looking at a sample population with greater variance (i.e., equal number of yield grades for equation development) and having VPS 2000 images available from each primal surface to provide independent variables representative of the entire carcass, is justifiable."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["born digital","masters theses"]},{"key":"dc:title","label":"Title","values":["Prediction of primal and subprimal beef yields with video image analysis"]}]}],"canonical_facts":{"dc:creator":["Nunes, Trevor Francis, author","Belk, Keith Evan, 1961-, advisor","Tatum, J. Daryl, committee member","Smith, Gary C., committee member","Chapman, Phillip L., committee member"],"dc:date.accessioned":["2007-01-03T05:16:14Z"],"dc:date.available":["2007-01-03T05:16:14Z"],"dc:date.issued":["2011"],"dc:description.abstract":["An ability to segregate carcasses based on both primal and subprimal yields would further facilitate value-based marketing in the beef industry. This study was conducted to evaluate Video Image Analysis (VIA) output to predict fabricated primal and subprimal yields. Carcasses were selected based on yield grade (YG 1, YG 2, YG 3, YG 4, and YG 5) as well as hot carcass weight (< 341 kg and ≥ 341 kg). A yield dissection was performed and at each step in fabrication, recovered product weights for each carcass to remain in the study summed to ≥ 99 % of the starting chilled weight of each primal and subprimal. For yield predictions, VIA output from 12th/13th rib interface images from the VBG 2000 (single-component; n = 142, development; n = 58, validation), or from VBG 2000 output in combination with output from loin/round primal interface images from the VPS 2000 (dual-component; n = 129, development; n = 56, validation) were regressed on yields of fabricated primals and subprimals. Yield variables were predicted as a percent of the aggregate chilled carcass side weight. Results from prediction equations for primals or the largest subprimal representing a primal in the study, indicated moderate and low predictive capability for development and validation datasets, respectively. For the square cut chuck (IMPS 113), commodity iii trimmed brisket (IMPS120, PS0 1), ribeye (IMPS 112A, PSO 3, 5.1 cm x 5.1 cm lip-on), short plate (IMPS 121), loin primal (IMPS 172), flank primal, and round primal (IMPS 158) R2 / adjusted R2 values (development / validation) of 0.39 / 0.11, 0.16 / 0.05, 0.31 / 0.12, 0.40 / 0.03, 0.56 / 0.12, 0.35 / -.005, and 0.64 / -0.05, respectively, for single-component predictions and 0.60 / -0.13, 0.57 / -0.03, 0.40 / 0.08, 0.52 / -0.15, 0.66 / -3.42, 0.66 / -3.42, 0.47 / -0.004, and 0.73 / -0.10, respectively, for dual-component predictions was observed. The best performing single-component model was for the tenderloin (IMPS 189A) with R2 / adjusted R2 values (development / validation) of 0.42 / 0.50. The best performing dual component model was for the cap off inside round (IMPS 169A) with R2 values (development / validation) of 0.58 / 0.30. The ability of single-component and dual-component equations to predict yields of several primal and subprimal cuts, with reasonable accuracy and precision in the development dataset, yet low accuracy and precision in the validation dataset, suggests that the VIA systems tested in this study do not have the potential as tool for more sensitive carcass segregation at this time. Further investigation to reveal the full potential of dual-component primal and subprimal cut yield prediction, perhaps looking at a sample population with greater variance (i.e., equal number of yield grades for equation development) and having VPS 2000 images available from each primal surface to provide independent variables representative of the entire carcass, is justifiable."],"dc:format.medium":["born digital","masters theses"],"dc:identifier":["Nunes_colostate_0053N_10387.pdf"],"dc:identifier.uri":["http://hdl.handle.net/10217/47436","https://doi.org/10.25675/3.018759"],"dc:language":["English"],"dc:language.iso":["eng"],"dc:publisher":["Colorado State University. Libraries"],"dc:rights":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."],"dc:subject":["subprimal yield","primal yield","video image analysis","beef","cutability"],"dc:title":["Prediction of primal and subprimal beef yields with video image analysis"],"dc:type":["Text"],"thesis:degree_discipline":["Animal Sciences"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science (M.S.)"],"thesis:institution_name":["Colorado State University"]},"updated_at":"2026-07-27T19:13:14Z"}