Graph-Based Semantic Segmentation for 3D Digital Images

Graph-based segmentation is gaining popularity among the many approaches in performing image segmentation, primarily due to its ability in reflecting global image properties. The most fundamental challenge in segmentation algorithm is to precisely define the volumetric extent of some object, which may be represented by the union of multiple regions. We developed a unified framework for volumetric image segmentation and contour extraction that uses a virtual tree-hexagonal structure defined on the set of the image voxels. The most important characteristic of using a virtual tree-hexagonal network over the initial image voxels is that it reduces the execution time and the memory space used, without losing the initial resolution of the image.