Explicit topological priors for deep-learning based image segmentation using persistent homology.
James R. CloughIlkay ÖksüzNicholas ByrneJulia A. SchnabelAndrew P. KingPublished in: CoRR (2019)
Keyphrases
- persistent homology
- deep learning
- image segmentation
- morse theory
- topological features
- computational geometry
- unsupervised learning
- unsupervised feature learning
- graph cuts
- machine learning
- markov random field
- multiscale
- computer vision
- image processing
- shape prior
- level set
- computer graphics
- object segmentation
- information extraction
- active contours
- energy function
- mobile robot
- mental models
- pairwise
- data mining
- feature selection
- learning algorithm