Fig. 2
From: Hyperspectral imaging: a novel approach for plant root phenotyping
Scheme of the image processing pipeline developed for root segmentation and chemometric analysis of root and soil properties from hyperspectral images. Implemented approaches for a pre-processing and b post-processing and image analysis. Abbreviations: ALS asymmetric least squares correction, SNV standard normal variate, MSC multiplicative scatter correction, EMSC extended multiplicative signal correction, SCR simple contrast ratio, WC Weber contrast, MC Michelson contrast, PCA principal component analysis, fft fast Fourier transform, ECOC error correcting output codes, PCR principal component regression, PLSR partial least squares regression, SVMR support vector machine regression. (The Matlab scripts can be obtained from the corresponding author upon request.)