Skip to main content
. 2019 Jul 31;2019:7368761. doi: 10.34133/2019/7368761

Figure 8.

Figure 8

Visualisation of the segmentation result for the 2016 image series. (a) Original image. (b) Ground truth (GT). (c) The result of trained FCN-8 from scratch. (d) The result of trained FCN-8 by loading pretrained ImageNet parameters (from left to right, images were selected to represent different key growth stages).