COMPUTER VISION SEGMENTATION OF THE LONGISSIMUS DORSI FOR BEEF QUALITY GRADING

摘要: A computer vision system was developed to support automation of beef quality grading. Images steaks were acquired for algorithm development. Fat and lean were differentiated using a fuzzy c-means clustering algorithm. Segmentation of the longissimus dorsi (l.d.) muscle is required because experts assign grades based primarily on visual appraisal l.d. robust segmentation convex hull procedures. The segmented from steak morphological operations erosion dilation. At end each iteration dilation, a fitted image, compactness measured. Iterations continued yield most compact l.d. Classification error in 1.97%. Average pixel distance by vision system 4.4 pixels.