Dealing with Topological Information Within a Fully Convolutional Neural Network
2018
A fully
convolutional neural networkhas a
receptive fieldof limited size and therefore cannot exploit global information, such as topological information. A solution is proposed in this paper to solve this problem, based on pre-processing with a geodesic operator. It is applied to the segmentation of histological images of pigmented reconstructed epidermis acquired via Whole Slide Imaging.
Keywords:
-
Correction
-
Source
-
Cite
-
Save
9
References
2
Citations
NaN
KQI