Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images

Table 1 Classification accuracy using different dimensionality reduction methods

Feature space	Bands	VNIR	SWIR
Normalized spectral*	All	0.980 ± 0.006	0.853 ± 0.027
PCA	All	0.968 ± 0.008	0.999 ± 0.002
Adaptive PCA	All	0.969 ± 0.007	0.996 ± 0.004
Custom	3	0.981 ± 0.008	0.997 ± 0.003
RGB	3	0.972 ± 0.009	–
CIR	3	0.971 ± 0.009	–
SWIR	3	–	0.999 ± 0.003
LDA	All	0.998 ± 0.003	0.998 ± 0.005

Principal Component Analysis (PCA) and standard band selections (RGB, CIR, SWIR) are compared to adaptive reduction methods. Adaptive PCA is based on stratified sampling based on class labels, custom band selection is based on relevance profiles and uses only three most relevant individual bands, while Linear Discriminant Analysis (LDA) is used to find an optimal subspace projection of the data
* Pixel-based segmentation of normalized spectra as reference, all other are spatial-spectral-based