Application of hyperspectral imaging technology in nondestructive testing of fruit quality

Abstract

Hyperspectral imaging (HSI) technology is a multidimensional information acquisition technology that combines imaging and spectroscopic techniques. It can not only visually display the external quality characteristics of the objects to be measured, but also reflect the differences in their internal chemical composition. HSI is playing an increasingly important role in rapid and non-destructive testing of fruit quality. In this paper, we discuss the application of HSI in the identification of small tomato varieties and the detection of pesticide residues. The back propagation neural network (BPNN) and support vector machine (SVM) algorithms were used to establish the variety identification and pesticide residues concentration analysis models. By using multiplicative scatter correction (MSC) pretreatment the accuracy of the two models reached up to 100%. The current study indicates that combining HSI technology with proper algorithm can provide an efficient method to identify small tomato varieties and detect pesticide residues.