Plant Phenomics / 2019 / Article / Fig 3

Research Article

An Exploration of Deep-Learning Based Phenotypic Analysis to Detect Spike Regions in Field Conditions for UK Bread Wheat

Figure 3

The training, validation, and testing strategy for developing Fully Convolutional Networks (FCN). (a) The selection of subimages for manually labelling spike regions, (b) training an FCN to segment spike regions with the manual labelled data, and (c) performing model testing at the image level to predict spikes.