Online Non-destructive Detection of Jujuble to Classify Infested and Intact Groups Based on NearInfrared Diffuse Reflection Spectra Analysis Technique

Abstract

Near-infrared reflectance spectroscopy (NIR) is an emerging kind of non-destructive detection method and become increasing popularity in the food industry. This work uses diffuse reflectance spectrum of NIR as sample to study the qualitative analysis of jujube, and try to find if it can classify infested and intact jujubes efficiently. Mahalanobis distance discriminant is used to build qualitative analysis model. The date of near infrared spectrum usually has a series of noise. The effects of different spectral pretreatment methods on the results of spectral analysis are studied for de-noising and resolution enhancement. The correctness of classification of original spectrum is 87.08%, and it is improved by 2-8% after date pretreatment in both calibration and prediction set. The best result is 96.67%. NIR is illustrated could be applied to classify jujubles.