Table 2.

Classification accuracy versus maximum block size for spatial feature extraction

	1	5	20	50	100
RGB	0.767 ± 0.013	0.938 ± 0.014	0.952 ± 0.011	0.964 ± 0.01	0.972 ± 0.009
LDA VNIR	0.782 ± 0.016	0.865 ± 0.016	0.951 ± 0.015	0.984 ± 0.007	0.998 ± 0.003
SWIR	0.617 ± 0.027	0.729 ± 0.047	0.872 ± 0.019
LDA SWIR	0.948 ± 0.017	0.986 ± 0.009	0.993 ± 0.006

With increasing maximum block size (from left to right) a gain in accuracy was achieved by introducing additional spatial-spectral features. Due to the different resolution of the cameras for the VNIR and SWIR domains, 100 × 100 pixels in the VNIR camera image match 20 × 20 pixels in the SWIR camera image of the same bunch. These two block sizes correspond to the approximate size of a single berry in the measurement set-up used. The rows RGB and SWIR refer to spatial features derived from selected bands, while rows LDA VNIR and LDA SWIR refer to texture features derived from projected images. For the VNIR wavelength range the spatial component contributes most to the accuracy gain, while in the SWIR wavelength range classification of spatial features from projected images outperformed classification based on spatial features from selected bands. Even by introducing only a few spatial features (maximum block size 5 pixels), a significant gain in classification accuracy was observed. Due to the different spatial resolution of VNIR and SWIR images, which is related to the different number of pixels and pixel sizes, the increase of the block size was limited to the approximate size of a single Chardonnay berry (VNIR 100 × 100, SWIR 20 × 20 pixels)