A Continuous Max-Flow Approach to Multi-Labeling Problems under Arbitrary Region Regularization

Autor:	Baxter, John S. H., Rajchl, Martin, Yuan, Jing, Peters, Terry M.
Rok vydání:	2014
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	The incorporation of region regularization into max-flow segmentation has traditionally focused on ordering and part-whole relationships. A side effect of the development of such models is that it constrained regularization only to those cases, rather than allowing for arbitrary region regularization. Directed Acyclic Graphical Max-Flow (DAGMF) segmentation overcomes these limitations by allowing for the algorithm designer to specify an arbitrary directed acyclic graph to structure a max-flow segmentation. This allows for individual 'parts' to be a member of multiple distinct 'wholes.' Comment: 10 pages, 2 figures, 3 algorithms - v2: Fixed typos / grammatical errors and mathematical errors in the primal/dual formulation. Extended methods for weighted DAGs rather than DAGs with edge multiplicity
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1405.0892 Zobrazit plný text záznamu View this record from Arxiv