Video image analysis as a predictor of beef carcass red meat yield percentage

Abstract

An improved ability to predict differences in the fabrication yields of beef carcasses would facilitate the application of value-based marketing. The first part of this study was conducted to evaluate the ability of the Dual-Component Australian VIASCAN™: (1) to predict fabricated beef subprimal yields as a percentage of carcass weight at each of three fat-trim levels and (2) to augment USDA yield grading, thereby improving accuracy of grade placement. Steer and heifer carcasses (n = 240) were evaluated using VIASCAN™, as well as by USDA expert and online graders, before fabrication of carcasses to each of three fat-trim levels. Cutability prediction using: (a) Expert yield grade, (b) online yield grade, (c) VIASCAN™ estimate of yield, and (d) VIASCAN™ augmented yield grade (using expert grader estimates of adjusted fat thickness and percentage of kidney-pelvic-heart fat, actual hot carcass weight and VIASCAN™ estimate of ribeye area), respectively: (1) accounted for 51, 37, 46, and 55% of the variation in fabricated yields of commodity-trimmed (2.54 cm.-trim) subprimals, (2) accounted for 74, 54, 66, and 75% of the variation in fabricated yields of closely trimmed (.64 cm.-trim) subprimals, and (3) accounted for 74, 54, 71 and 75% of the variation in fabricated yields of very closely trimmed (<.64 cm.-trim) subprimals. The VIASCAN™ estimate of yield predicted fabrication yields more accurately than online yield grade and, the VIASCAN™ -augmented yield grade improved the accuracy of cutability prediction, at packing plant line speeds, to a level matching that of expert graders applying grades at a comfortable rate. The second part of this study was conducted to evaluate the ability of a commercial VIA system, the Canadian Computer Vision System (CVS™) : (1) to predict yields of commercially fabricated beef subprimals as a percentage of carcass weight and (2) to augment USDA yield grading, to improve accuracy of grade placement. The CVS™ was evaluated as a completely installed production system operating on a full-time basis at chain-speeds. Steer and heifer carcasses (n = 296) were evaluated using CVS™, as well as by USDA expert and online graders, before fabrication of carcasses to closely trimmed subprimal cuts. Expert yield grade, online yield grade, CVS™ estimate of yield, and CVS™-augmented yield grade (using expert grader estimates of adjusted fat thickness and percentage of kidney-pelvic-heart fat, actual hot carcass weight and VIASCAN™ estimate of ribeye area), respectively, accounted for 67, 39, 64, and 65% of the variation in fabricated yields of closely trimmed subprimals. The CVS™ estimate of yield predicted fabrication yields more accurately than online yield grade and, the CVS™ augmented yield grade improved the accuracy of cutability prediction, under packing plant conditions and speeds, to a level close to that of expert graders applying grades without time pressure.