Submitted to: Journal of Animal Science
Publication Type: Peer reviewed journal
Publication Acceptance Date: 8/20/2002
Publication Date: 1/20/2003
Citation: Shackelford, S.D., Wheeler, T.L., Koohmaraie, M. 2003. On-line prediction of yield grade, longissimus muscle area, preliminary yield grade, adjusted preliminary yield grade, and marbling score using the MARC beef carcass image analysis system. Journal of Animal Science. 81:150-155. Interpretive Summary: There is a large amount of variation between beef carcasses in the yield of lean meat. To encourage the production of more valuable carcasses, beef packing companies would like to pay producers a premium for carcasses that excel in lean meat yield. Currently, the lean meat yield of a carcass is estimated by USDA graders, who typically have approximately 9 seconds to visually evaluate a carcass and apply a grade. Because of the subjectivity of the current method of carcass grading, the industry and USDA have made the development of a system to objectively determine carcass value a high priority. The Agricultural Research Service and IBP Inc. entered into a Cooperative Research and Development Agreement to develop an instrument to determine the yield grade of a beef carcass. Our study showed that the resulting system could accurately determine beef carcass yield grades and, thus, should help facilitate value-based marketing of beef.
Technical Abstract: The present experiment was conducted to evaluate the ability of the MARC Beef Carcass Image Analysis System to predict calculated yield grade, longissimus area, preliminary yield grade, adjusted preliminary yield grade, and marbling score under commercial beef processing conditions. In two commercial beef processing facilities, image analysis was conducted on 800 carcasses on the beef grading chain immediately after the conventional USDA beef quality and yield grades were applied. Carcasses were blocked by plant and observed calculated yield grade and then 400 carcasses were assigned to a calibration data set, which was used to develop regression equations, and 400 carcasses were assigned to a prediction data set, which was used to validate the regression equations. Prediction equations, which included image analysis variables and hot carcass weight, accounted for 90%, 88%, 90%, 88%, and 76% of the variation in calculated yield grade, longissimus area, preliminary yield grade, adjusted preliminary yield grade, and marbling score in the prediction data set. In comparison, the official USDA yield grade as applied by on-line graders accounted for 73% of the variation in calculated yield grade. The technology described herein could be used by the beef industry to more accurately determine beef yield grades; however, this system does not provide an accurate enough prediction of marbling score to be used without USDA grader interaction for USDA quality grading.