Automatic optimization of regions of interest in hyperspectral images for detecting vegetative indices in soybeans

Vegetative indices (VIs) are widely used in high-throughput phenotyping (HTP) for the assessment of plant growth conditions; however, a range of VIs among diverse soybeans is still an unexplored research area. For this reason, we investigated a range of four major VIs: normalized difference vegetation index (NDVI), photochemical reflectance index (PRI), anthocyanin reflectance index (ARI), and change to carotenoid reflectance index (CRI) in diverse soybean accessions. Furthermore, we ensured the correct positioning of the region of interest (ROI) on the soybean leaf and clarified the effect of choosing different ROI sizes. We also developed a Python algorithm for ROI selection and automatic VIs calculation. According to our results, each VI showed diverse ranges (NDVI: 0.60-0.84, PRI: -0.03 to 0.05, ARI: -0.84 to 0.85, CRI: 2.78-9.78) in two different growth stages. The size of pixels in ROI selection did not show any significant difference. In contrast, the shaded part and the petiole part had significant differences compared with the non-shaded and tip, side, and center of the leaf, respectively. In the case of the Python algorithm, algorithm-derived VIs showed a high correlation with the ENVI software-derived value: NDVI -0.97, PRI -0.96, ARI -0.98, and CRI -0.99. Moreover, the average error was detected to be less than 2.5% in all these VIs than in ENVI.