Predicting beef tenderness using color and multispectral image texture features

• Published in: Meat science Vol. 92; no. 4; pp. 386 - 393
• Main Authors: Sun, X., Chen, K.J., Maddock-Carlin, K.R., Anderson, V.L., Lepper, A.N., Schwartz, C.A., Keller, W.L., Ilse, B.R., Magolski, J.D., Berg, E.P.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.12.2012; Elsevier
• Subjects: Animal Feed - analysis; Animals; Artificial Intelligence; Beef; Biological and medical sciences; Cattle; Chemical Phenomena; Color; Crosses, Genetic; Female; Food industries; Food Inspection - methods; Fourier Analysis; Fundamental and applied biological sciences. Psychology; Hot Temperature; Image Processing, Computer-Assisted; Meat - analysis; Meat - classification; Meat and meat product industries; Mechanical Phenomena; Multispectral image; Neural Networks, Computer; Pigmentation; Pisum sativum - chemistry; Reproducibility of Results; Seeds - chemistry; Shear Strength; Spectrophotometry; Stepwise; Surface Properties; SVM; Tenderness; Multispectral image; Beef; SVM; Tenderness; Color; Stepwise; Meat product; Texture
• ISSN: 0309-1740; 1873-4138
• DOI: 10.1016/j.meatsci.2012.04.030

The objective of this study was to investigate the usefulness of raw meat surface characteristics (texture) in predicting cooked beef tenderness. Color and multispectral texture features, including 4 different wavelengths and 217 image texture features, were extracted from 2 laboratory-based multispectral camera imaging systems. Steaks were segregated into tough and tender classification groups based on Warner–Bratzler shear force. The texture features were submitted to STEPWISE multiple regression and support vector machine (SVM) analyses to establish prediction models for beef tenderness. A subsample (80%) of tender or tough classified steaks were used to train models which were then validated on the remaining (20%) test steaks. For color images, the SVM model correctly identified tender steaks with 100% accurately while the STEPWISE equation identified 94.9% of the tender steaks correctly. For multispectral images, the SVM model predicted 91% and STEPWISE predicted 87% average accuracy of beef tender. ► Longissimus, semimembranosus, biceps femoris, and supraspinatus steaks were obtained. ► Steaks were from crossbred heifers supplemented with different field pea components. ► Color and multispectral image texture features were used to classify tenderness. ► Regression and support vector machine analyses increased the model accuracy.