Skip to main content
Fig. 9 | Plant Methods

Fig. 9

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

Fig. 9

Classification results. Confusion matrices for thresholds corresponding to the operating points with maximum accuracy (see Fig. 8) of spectral (left) and spatial-spectral classification (right). For spatial-spectral classification, thresholds are found which allow perfect detection of healthy and severely diseased grape bunches. Also, the false detections of infected bunches as healthy and as severely infected are reduced by the spatial-spectral approach. The best automatically obtained decisions differ from visual assessment by experts only for 4 of the 10 infected bunches, with 3 classified as healthy and 1 classified as severely diseased. In addition, operating points can be adjusted according to application demands to provide a lower total accuracy but higher specificity/sensitivity for a certain class as needed

Back to article page

Plant Methods

ISSN: 1746-4811