A novel approach to grading pork carcasses: computer vision and ultrasound |
| |
Authors: | Fortin A Tong A K W Robertson W M Zawadski S M Landry S J Robinson D J Liu T Mockford R J |
| |
Affiliation: | Agriculture and Agri-Food Canada, Lacombe Research Centre, Lacombe, Alberta, Canada T4L 1W1 |
| |
Abstract: | A Computer Vision System prototype for grading pork carcasses was developed at the Lacombe Research System. The system consists of two components: ultrasound imaging to scan a cross-section of the loin muscle and video imaging to capture two-dimensional (2D) and three-dimensional (3D) images of the carcass. For each of the 241 carcasses (114 barrows and 127 gilts), salable meat yield was determined from a full cutout. Linear, two- and three-dimensional, angular and curvature measurements and carcass volume were derived from each image. Muscle area and fat thickness (7 cm off the mid-line) measured by ultrasound at the next to last rib site, together with 2D and 3D measurements provided the most accurate model for estimating salable meat yield (R2=0.82 and RSD=1.68). Models incorporating fat thickness and muscle depth measured at the Canadian grading site (3/4 last rib, 7 cm off the mid-line) with the Destron PG-100 probe, had the lowest R2 and highest residual standard deviation (RSD) values (R2=0.66 and RSD=2.15). Cross-validation demonstrated the reliability and stability of the models; hence conferring them good industry applicability. The Lacombe Computer Vision System prototype appears to offer a marked improvement over probes currently used by the Canadian pork industry. |
| |
Keywords: | Computer vision Ultrasound Pork grading |
本文献已被 ScienceDirect PubMed 等数据库收录! |
|