Combining computer vision score and conventional meat quality traits to estimate the intramuscular fat content using machine learning in pigs. (March 2022)

• Record Type: Journal Article
• Authors: Chen, Dong; Wu, Pingxian; Wang, Kai; Wang, Shujie; Ji, Xiang; Shen, Qi; Yu, Yang; Qiu, Xiaotian; Xu, Xu; Liu, Yihui; Tang, Guoqing
• Is Part Of: Meat science. Volume 185(2022)
• Publication Date: 2022-03
• Subjects: Computer vision -- Intramuscular fat -- Stepwise regression -- Machine learning; Meat -- Periodicals; Meat industry and trade -- Periodicals; Viande -- Périodiques; Viande -- Industrie -- Périodiques; Meat; Meat industry and trade; Periodicals; 641.36
• DOI: 10.1016/j.meatsci.2021.108727
• Languages: English
• ISSNs: 0309-1740

Abstract

Abstract: Intramuscular fat content (IMF%) is an important factor that affects the quality of pork. The traditional testing method (Soxhlet extraction) is accurate; however, it has a long preprocessing time. In this study, a total of 1481 photographs of 200 pigs' loin muscles were used to obtain a computer vision score (IIMF %). Then, actual IMF%, meat color, marbling score, pH value, and drip loss of 200 pigs were measured. Stepwise regression (SR) and gradient boosting machine (GBM) were used to construct the estimation model of IMF%. The results showed that the correlation coefficients between IMF% and IIMF%, marbling score, backfat thickness, percentage of moisture (POM), and pH value were 0.68, 0.64, 0.48, 0.45, and 0.25, respectively. The model accuracies of SR and GBM base on residuals distribution were 0.875 and 0.89, respectively. This study presents a method for estimating IMF% using computer vision technology and meat quality traits. Highlights: 6–10 photos per pig to enhance the representation of eye muscle images. Adding muscle and fat density to the IIMF% formula to improve the representation of IIMF%. Adding meat quality traits to prediction factor of model to Improve model accuracy. Comparison of IMF Estimation Models by Stepwise Regression and GBM.