Skip to main content
Fig. 3 | Plant Methods

Fig. 3

From: Experimental data manipulations to assess performance of hyperspectral classification models of crop seeds and other objects

Fig. 3

Results from experimental performance assessments of classification models. Training data set from tomato variety 1 was manipulated in three different ways, and for each manipulation, we examined the effect on accuracy of linear discriminant (LDA) and support vector machine (SVM) classification models (based on ten-fold cross validation). Object assignment error: effect of individual seeds being assigned to the wrong class (a). Spectral repeatability: effect of introducing known levels of stochastic noise to individual reflectance values (b). Size of training data set: effect of randomly reducing the number of observations in the training data set (c)

Back to article page