000186163 001__ 186163
000186163 005__ 20190812205701.0
000186163 02470 $$2ISI$$a000331094301112
000186163 0247_ $$2doi$$a10.1109/Cvpr.2013.238
000186163 037__ $$aCONF
000186163 245__ $$aReconstructing Loopy Curvilinear Structures Using Integer Programming
000186163 269__ $$a2013
000186163 260__ $$bIeee$$aNew York$$c2013
000186163 336__ $$aConference Papers
000186163 520__ $$aWe propose a novel approach to automated delineation of linear structures that form complex and potentially loopy networks. This is in contrast to earlier approaches that usually assume a tree topology for the networks. At the heart of our method is an Integer Programming formulation that allows us to find the global optimum of an objective function designed to allow cycles but penalize spurious junctions and early terminations. We demonstrate that it outperforms state-of-the-art techniques on a wide range of datasets.
000186163 6531_ $$aLoopy Curvilinear Structures
000186163 6531_ $$aCurvilinear Structure Reconstruction
000186163 6531_ $$aGlobal Optimization
000186163 6531_ $$aQuadratic Minimum Arborescence
000186163 6531_ $$aPath Classification
000186163 700__ $$0242718$$g183992$$aTüretken, Engin
000186163 700__ $$0244089$$g198495$$aBenmansour, Fethallah
000186163 700__ $$aAndres, Bjoern
000186163 700__ $$aPfister, Hanspeter
000186163 700__ $$0240252$$g112366$$aFua, Pascal
000186163 7112_ $$dJune, 2013$$cPortland, Oregon, USA$$aConference on Computer Vision and Pattern Recognition (CVPR)
000186163 773__ $$tProceedings of IEEE Conference on Computer Vision and Pattern Recognition
000186163 8564_ $$zURL$$uhttp://cvlab.epfl.ch/research/medical/lm
000186163 8564_ $$zn/a$$yn/a$$uhttps://infoscience.epfl.ch/record/186163/files/turetken_et_al.pdf$$s3370567
000186163 909C0 $$xU10659$$pCVLAB$$0252087
000186163 909CO $$ooai:infoscience.tind.io:186163$$qGLOBAL_SET$$pconf$$pIC
000186163 917Z8 $$x183992
000186163 917Z8 $$x112366
000186163 937__ $$aEPFL-CONF-186163
000186163 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000186163 980__ $$aCONF