Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
8502607 | Meat Science | 2018 | 29 Pages |
Abstract
The objective of this study was to investigate the ability of computer vision system to predict pork intramuscular fat percentage (IMF%). Center-cut loin samples (nâ¯=â¯85) were trimmed of subcutaneous fat and connective tissue. Images were acquired and pixels were segregated to estimate image IMF% and 18 image color features for each image. Subjective IMF% was determined by a trained grader. Ether extract IMF% was calculated using ether extract method. Image color features and image IMF% were used as predictors for stepwise regression and support vector machine models. Results showed that subjective IMF% had a correlation of 0.81 with ether extract IMF% while the image IMF% had a 0.66 correlation with ether extract IMF%. Accuracy rates for regression models were 0.63 for stepwise and 0.75 for support vector machine. Although subjective IMF% has shown to have better prediction, results from computer vision system demonstrates the potential of being used as a tool in predicting pork IMF% in the future.
Related Topics
Life Sciences
Agricultural and Biological Sciences
Food Science
Authors
J.-H. Liu, X. Sun, J.M. Young, L.A. Bachmeier, D.J. Newman,