Fig. 9From: An image analysis pipeline for automated classification of imaging light conditions and for quantification of wheat canopy cover time series in field phenotypingBoxplots of three quality measures, Qseg (a), Sr (b) and Es (c), showing the performance of for canopy cover segmentation using the μRow, Otsu and three types of ML-based models (MALC, MHLC, MLLC models using DT and SVM algorithms), which were evaluated on 20 LLC images (Class 1) and 20 HLC images (Class 2). Non-overlapped box notches indicate significant differences between the segmentation methods, with 95% confidence. The 40 reference images for validation are publicly available in the ‘figshare’ repository [30]Back to article page