Predicting pork loin intramuscular fat using computer vision system

Meat Sci. 2018 Sep:143:18-23. doi: 10.1016/j.meatsci.2018.03.020. Epub 2018 Mar 26.

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 (n = 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.

Keywords: Computer vision system; Intramuscular fat; Stepwise regression; Support vector machine.

Publication types

  • Comparative Study
  • Evaluation Study

MeSH terms

  • Algorithms
  • Animals
  • Artificial Intelligence
  • Consumer Behavior
  • Dietary Fats / analysis*
  • Discriminant Analysis
  • Food Inspection / instrumentation
  • Food Inspection / methods*
  • Food Preferences
  • Food Quality*
  • Humans
  • Machine Learning
  • Meat / analysis*
  • Models, Biological*
  • Muscle, Skeletal / chemistry*
  • Pigments, Biological / analysis
  • Regression Analysis
  • Reproducibility of Results
  • Statistics as Topic
  • Support Vector Machine
  • Sus scrofa

Substances

  • Dietary Fats
  • Pigments, Biological