AUTHOR=Li Ang , Li Chenxi , Gao Moyang , Yang Si , Liu Rong , Chen Wenliang , Xu Kexin 

TITLE=Beef Cut Classification Using Multispectral Imaging and Machine Learning Method

JOURNAL=Frontiers in Nutrition

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/nutrition/articles/10.3389/fnut.2021.755007

DOI=10.3389/fnut.2021.755007

ISSN=2296-861X

ABSTRACT=Classification of beef cuts is important for the processing industry and authentication purposes. The traditional analysis methods are time constraints and incompatible with the modern food industry. Taking the advantages of rapidness and non-destructive, multiple-spectral imaging (MSI) has been widely applied to obtain a precise characterization of food and agriculture products. This study aims at developing the classification model for beef cuts by using MSI and machine learning classifiers. The beef samples are measured with a snapshot multi-spectroscopic camera within the range of 500–800 nm. In order to find a more accurate classification model, single-feature and multiple-modality feature sets are used to develop an accurate classification model with different machine learning-based classifiers, including discriminant analysis (LDA), support vector machine (SVM), and random forest (RF) algorithms. The results demonstrated that the optimum developed LDA classifier achieves the prediction accuracy of over 90% with multiple-modality feature fusion. By combining machine learning and feature fusion, the other classification models also achieve satisfying accuracy. Furthermore, this work demonstrates the potential of machine learning and feature fusion method for meat classification from multiple spectral imaging in future agricultural applications.