Search

Identifying the geographic origin of peaches will not only help producers obtain higher economic benefits, but also enable consumers to buy the most satisfactory fruits. In this study, the feasibility of distinguishing the geographic origin of four traditional famous peaches in China by visible-near infrared spectroscopy, fluorescence spectroscopy and image processing technology was explored. Visible-near infrared spectra and fluorescence spectra of 397–1175 nm and color characteristics extracted from images were used to establish the support vector machine, k-nearest neighbor, random forest and extreme learning machine classification models. The factors most related to the geographic origin were found by decision tree analysis. The results showed that the support vector machine models had the highest classification accuracy, some reaching 100%. In order to improve the calculation speed, the spectral principal components were used, resulting in the accuracy of support vector machine, k-nearest neighbor and random forest models more than 95%. The decision tree showed that R value, the first principal component of fluorescence spectra and H value played a decisive role in identifying the geographic origin, leading to the accuracy of support vector machine, k-nearest neighbor and random forest models more than 95%. This study compared the advantages and disadvantages of visible-near infrared spectroscopy, fluorescence spectroscopy and image processing technology in identifying geographic origin, and found that the combination of these three methods could effectively distinguished the geographic origin of peaches. • The quality attributes of peaches from different geographic origins were compared. • Three non-destructive methods were compared in identifying the geographic origins. • The SVM models based on spectral and image data had the highest accuracy. • Three factors most related to geographic origin of peaches were found. [ABSTRACT FROM AUTHOR]