Evaluation of the E+V video image analysis system as a predictor of pork carcass meat yield1

• Published in: Journal of animal science 2003-05, Vol.81 (5), p.1193-1201
• Main Authors: McClure, E. K., Scanga, J. A., Belk, K. E., Smith, G. C.
• Format: Article
• Language: English
• Subjects: Image processing systems; Measuring instruments; Meat products; Pork; Product quality; Weight
• ISSN: 0021-8812; 1525-3163
• DOI: 10.2527/2003.8151193x

This study was conducted to assess the ability of the VCS2001 (E+V, Oranienburg, Germany) video image analysis system to predict pork carcass composition. Pork carcasses (n = 278) were selected from a commercial packing plant to differ in weight, Fat-O-Meater (FOM) predicted percentage lean, and gender. Carcasses were imaged three times with the VCS2001, chilled overnight, and then sequentially fabricated into boneless subprimals. The VCS2001 accurately predicted the weight of total saleable product (R^sup 2^ = 0.88, root mean square error [RMSE] = 1.84) and fat-corrected lean (R^sup 2^ = 0.92, RMSE = 1.66), but autocorrelation existed between dependent and independent variables. The VCS2001 was acceptably accurate and precise in predicting weights of bone-in ham (R^sup 2^ = 0.83, RMSE = 0.80), bone-in loin (R^sup 2^ = 0.74, RMSE = 1.17), loin lean (R^sup 2^ = 0.77, RMSE = 0.82), belly (R^sup 2^ = 0.78, RMSE = 0.94), sparerib (R^sup 2^ = 0.55, RMSE = 0.28), and boneless shoulder (R^sup 2^ = 0.73, RMSE = 0.79). Weights were more accurately predicted than yields (as a percentage of hot carcass weight) of total saleable product (R^sup 2^ = 0.47, RMSE = 1.97) or total fat-corrected lean (R^sup 2^ = 0.44, RMSE = 1.89) using VCS2002, and it did not accurately predict percentages of bone-in ham (R^sup 2^ = 0.45, RMSE = 1.13), ham lean (R^sup 2^ = 0.32, RMSE = 1.46), bone-in loin (R^sup 2^ = 0.29, RMSE = 1.36), loin lean (R^sup 2^ = 0.56, RMSE = 0.90), belly (R^sup 2^ = 0.43, RMSE = 1.08), sparerib (R^sup 2^ = 0.08, RMSE = 0.32), or boneless shoulder (R^sup 2^ = 0.30, RMSE = 0.88). New prediction models and equations were developed using VCS2001 output variables plus hot carcass weight to predict weight of total saleable product (R^sup 2^ = 0.89, RMSE = 1.72) and fat-corrected lean (R^sup 2^ = 0.93, RMSE = 1.55) with very minimal increases in accuracy and precision over that achieved using E+V-programmed models and equations. Use of new prediction models and equations marginally improved accuracy and precision of estimations of total saleable product yield (R^sup 2^ = 0.56, RMSE = 1.81) and fat-corrected lean yield (R^sup 2^ = 0.57, RMSE = 1.67) over that achieved using E+V-programmed models and equations. The VCS2001 was not able to predict pork carcass composition more accurately than existing technology; therefore, further development is needed to assure commercial viability of this instrument. [PUBLICATION ABSTRACT] Key Words: Carcass Composition, Instrumentat