[show abstract][hide abstract] ABSTRACT: In two phases, this study assessed the ability of two video image analysis (VIA) instruments, VIASCAN and Computer Vision System (CVS), to augment assignment of yield grades (YG) to beef carcasses to 0.1 of a YG at commercial packing plant speeds and to test cutout prediction accuracy of a YG augmentation system that used a prototype augmentation touchpanel grading display (designed to operate commercially in real-time). In Phase I, beef carcasses (n = 505) were circulated twice at commercial chain speeds (340 carcasses per hour) by 12 on-line USDA graders. During the first pass, on-line graders assigned a whole-number YG and a quality grade (QG) to carcasses as they would normally. During the second pass, on-line graders assigned only adjusted preliminary yield grades (APYG) and QG to carcasses, whereas the two VIA instruments measured the longissimus muscle area (LMA) of each carcass. Kidney, pelvic, and heart fat (KPH) was removed and weighed to allow computation of actual KPH percentage. Those traits were compared to the expert YG and expert YG factors. On-line USDA graders' APYG were closely related (r = 0.83) to expert APYG. Instrument-measured LMA were closely related (r = 0.88 and 0.94; mean absolute error = 0.3 and 0.2 YG units, for VIASCAN and CVS, respectively) to expert LMA. When YG were augmented using instrument-measured LMA and computed either including or neglecting actual KPH percentage, YG were closely related (r = 0.93 and 0.92, mean absolute error = 0.32 and 0.40 YG units, respectively, using VIASCAN-measured LMA; r = 0.95 and 0.94, mean absolute error = 0.24 and 0.34 YG units, respectively, using CVS-measured LMA) to expert YG. In Phase II, augmented YG were assigned (0.1 of a YG) to beef carcasses (n = 290) at commercial chain speeds using VIASCAN and CVS to determine LMA, whereas APYG and QG were determined by online graders via a touch-panel display. On-line grader YG (whole-number), expert grader YG (to the nearest 0.1 of a YG), and VIASCAN- and CVS-augmented YG (to the nearest 0.1 of a YG) accounted for 55, 71, 60, and 63% of the variation in fabricated yields of closely trimmed subprimals, respectively, suggesting that VIA systems can operate at current plant speeds and effectively augment official USDA application of YG to beef carcasses.
Journal of Animal Science 10/2003; 81(9):2239-46. · 2.09 Impact Factor
[show abstract][hide abstract] ABSTRACT: This study was conducted to determine the accuracy and repeatability of beef carcass longissimus muscle area (LMA) measurements obtained by three different methods. Longissimus muscle area for beef carcass sides (n = 100) randomly selected in a commercial packing plant was determined: 1) independently by three USDA grading supervisor "experts" using the grid method to obtain triplicate measurements of the same longissimus muscle (LM); 2) by three different Colorado State University personnel tracing the LMA on acetate paper and subsequently measuring the area via a polar planimeter three different times (total of 3 x 3 = 9 observations/LM); and 3) by use of two identical video image analysis (VIA) instruments making triplicate measurements for each LM using three different procedures. Video image analysis Procedure 1 required that LMA be measured by placing the camera head unit over the LM and collecting three sequential images without moving the camera head unit while carcasses were in a stationary position; Procedure 2 required measurement of LMA by placing the camera head unit over the LM and collecting three images, but removing and repositioning the camera head unit between collection of each image while carcasses were in a stationary position; and Procedure 3 required that LMA be measured by placing the camera head unit over the LM and obtaining an image while carcasses were in continuous motion (chain speed of 360 carcasses/ h) during three different circulations past the grading stand. Overall, VIA-derived LMA measurements were highly accurate for all three procedures compared with expert-gridded (R2 = 0.92, 0.90, and 0.84 for Procedures 1, 2, and 3, respectively) and acetate/planimeter-traced (R2 = 0.94, 0.93, and 0.86 for Procedures 1, 2, and 3, respectively) LMA measurements. Instrument LMA repeatability also was comparable to expert-gridded and acetate/planimeter-traced LMA repeatability, as the means of the absolute differences between individual measurements and the average of those same measurements per LM were 1.29, 1.35, 0.52, 0.84, and 1.87 cm2 for expert-gridded, acetate/planimeter-traced, and VIA Procedures 1, 2, and 3, respectively. Therefore, VIA instrumentation can be used to assess beef carcass LMA in both a stationary and operational scenario with high levels of accuracy and repeatability.
Journal of Animal Science 09/2003; 81(8):1980-8. · 2.09 Impact Factor
[show abstract][hide abstract] ABSTRACT: This project was conducted to test the applicability of using two state-of- art Video Image Analysis (VIA) instruments (the Australian VIAscan system, and the Canadian CVS system) to augment USDA line graders assignment of USDA Yield Grades (YG), to a tenth of a yield grade unit, at commercial packing plant speeds. Adjusted preliminary yield grade (PYG), and USDA yield grade were determined by twelve USDA line graders and supervisors for beef carcasses (n = 505) selected in a commercial beef packing plant. Data were compared (5,696 comparisons) to "Gold Standard" yield grades and yield grade factors determined by an expert panel of carcass evaluators given unrestrained time and access to carcasses. The beef carcasses were transferred across the grade chain for each set of USDA line graders twice; the first time the graders assigned a yield and quality grade as done normally, and the second time the graders assigned an adjusted PYG and a quality grade to each carcass. In addition, the two VIA instruments measured the ribeye area of each carcass on the grade chain. At the completion of the trial personnel from Colorado State University removed the kidney, pelvic, and heart fat (KPH) and determined the actual KPH percentage. Online USDA grader PYG were closely related (r = 0.83) to Gold Standard adjusted PYG's. VIAscan and CVS measured REA also were closely related (r = 0.88 and 0.94, respectively) to Gold Standard REA measurements. Two augmented yield grades were tested. The first was comprised of a line grader adjusted PYG, actual KPH percentage (simulating KPH removal and weighing on the slaughter floor), VIA measured ribeye area, and actual hot carcass weight. The second augmented YG was the same as the first, except KPH percentage was eliminated. Augmenting application of USDA yield grades, either by including actual KPH percentage, or neglecting it, were closely related (mean absolute error of .32 and .40 yield grade units; r = 0.93 and 0.92, respectively using VIAscan measured REA; mean absolute error of .24 and .34 yield grade units; r = 0.95 and 0.94, respectively using CVS measured REA) to Gold Standard yield grades. These results indicated that VIA systems can be used to help augment USDA Yield Grades at on- line chain speeds, and that using VIA technology to augment USDA line graders introduces the possibility of accurately assigning yield grades to a tenth of a yield grade unit in real time.