Application of Hyperspectral Technique for Color Classification Avocados Subjected to Different Treatments

Abstract

In this study, the applicability of hyperspectral technique, a fast and non-destructive, novel method was investigated for the color discrimination of avocados subjected to different treatments. Fruits like avocados are coated with edible films to extend their shelf life. Using different formulations of coating with varying pectin, beeswax, and sorbitol contents, nine different coating preparations with potential to influence the ripening behavior of avocados were developed. Avocados were coated with these formulations, air-dried, and stored at room temperature. Concurrently, the reflectance responses of the avocado fruits were measured in 2,151 wavebands (350 to 2500 nm) with a field spectroradiometer. To tackle the co-linearity that exists between the spectral observations, aggregated 10- and 20-nm data sets were used. Using a stepwise procedure, the most effective wavebands capable of discriminating treatment effects were selected. By applying a discrimination procedure with a well-chosen subset of the selected wavebands, treatments were correctly classified with more than 92% accuracy.