Date of this Version
Assessing meat yield and quality in carcasses is important for exporting meat and for the domestic consumer. The U.S. livestock and meat industries depend heavily on USDA to provide the rating of their meat for marketing. There is also a trend in the U.S. meat industry to process meat closer to the site of slaughter because of increasing transportation and energy costs. Only the edible portion of the carcass will leave the slaughter plant. These trends will increase the volume and demand for more consistent, equitable, and timely methods for grading meat.
Since the USDA meat grading system was first put into use in 1927, meat has been graded by human graders. Because grading is subjective in nature, it is very difficult (if not impossible) to achieve consistency and equity. The development of instruments to assist the human grader in evaluating grade factors has been strongly recommended.
Current developments in the expert systems and natural languages make it possible to devise systems to assist meat graders. At MARC we have initiated a project with an immediate objective of developing systems to assist graders in grading meat, and an ultimate objective of automating the meat grading process through applications of image processing, natural languages, pattern recognition, and expert systems technologies.
This paper describes a knowledge-based expert system which has been developed to assist meat graders in deciding beef carcass yield and quality grades.