Fig. 3.

Systematic approach and development of powdery mildew detection models. Based on hyperspectral images of visually healthy and severely diseased detached berries a dataset containing spectra of both classes is generated. Two different feature spaces are investigated for classification of spectral data; first, dimensionality reduction with subsequent spatial-spectral feature extraction and second, classification of complete spectral signatures. The path on the right corresponds to the first row of Table 1, whereas the left hand side corresponds to the remaining rows