The Western GCO Segmentation problem instances are provided to compare effects of graph size, neighborhood size, length of s to t paths, regional arc consistency (noise), and arc capacity magnitude. The graph construction is described in the papers: liver 128128119 adhead 256256192 babyface 25025081 bone (256256119) bone_subxyz (12812860) bone_subx (128256119) bone_subxyz_subx (6412860) bone_subxy (128128119) bone_subxyz_subxy (646460) abdomen_long 512512551 abdomen_short 512512551 References: [BJ01] Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D images. Yuri Boykov, Marie-Pierre Jolly. In International Conference on Computer Vision (ICCV), 1:105-112, 2001. [BF06] Graph Cuts and Efficient N-D Image Segmentation. Yuri Boykov, Gareth Funka-Lea. In International Journal of Computer Vision (IJCV), 70(2):109-131, 2006. [BK03] Computing Geodesics and Minimal Surfaces via Graph Cuts. Yuri Boykov, Vladimir Kolmogorov. In International Conference on Computer Vision (ICCV), 1:26-33, 2003. The liver, bone, abdomen, babyface volumetric scans were provided by Siemens Corporate Research; adhead volumetric scan was provided by Robarts Research Institute.

Related datasets