Predicting pork loin intramuscular fat using computer vision system.
Meat Sci
; 143: 18-23, 2018 Sep.
Article
em En
| MEDLINE
| ID: mdl-29684840
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.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Gorduras na Dieta
/
Qualidade dos Alimentos
/
Inspeção de Alimentos
/
Músculo Esquelético
/
Carne
/
Modelos Biológicos
Idioma:
En
Ano de publicação:
2018
Tipo de documento:
Article