Chlorophylls Content Prediction of Green Amaranth (Amaranthus tricolor L.) Leaves based on Vis-NIR Image

Hyperspectral imaging is a technology that combines the conventional imaging and spectroscopy to acquire both spectral and spatial information from the samples. In this study, a hyperspectral imaging in the spectral range of 400-1000 nm was used for chlorophyll content prediction of Green amaranth leaves based on reflectance profile. Spectral data in the region of interest (ROI) of each leaf were extracted from the hyperspectral images. The determination of total chlorophyll content was measured using spectrophotometer UV-Vis. The Partial least squares regression (PLSR) was used to create a model prediction between the measured chlorophyll content and the reflectance spectral. The correlation coefficients (r) in the full wavelength (400-1000 nm) for training and testing data is content is 0.9997 (r(2) = 0.9994) and 0.9156 (r(2) = 0.834), respectively. The result shows that the hyperspectral imaging could be used to predict chlorophyll content as a nondestructive test.