The edge and corner structures are two categories of perceptually important image characteristics, and hence, edge-and-corner preserving regularization is required for many problems in image processing. In this paper, the first novelty is to propose
LPP: Locality Preserving Projections % Note: After applying some simple algebra, the smallest eigenvalue problem: % data^T*L*data = \lemda data^T*D*data % is equivalent to the largest eigenvalue problem: % data^T*W*data = \beta data^T*D*data % where
Topology-Preserving Deep Image Segmentation
Segmentation algorithms are prone to make topological errors on fine-scale structures,
e.g., broken connections. We propose a novel method that learns to segment
with correct topology. In particular, we
