Skip to main content
. 2018 May 31;41(7):1559–1572. doi: 10.1109/TPAMI.2018.2840695

Fig. 2.

Fig. 2.

Input of R-Net in Stage 2. (a) The user provides clicks/scribbles to correct foreground (red) and background (cyan) on the initial automatic segmentation. (d) and (e) are geodesic distance maps based on foreground and background interactions, respectively. The original image (b) is combined with the initial automatic segmentation (c) and the geodesic distance maps (d), (e) by channel-concatenation and used as the input of R-Net.