Vector Image Segmentation Tools

Vector Image Segmentation Tools is a collection of C++ library, binary modules, and shell scripts for vector segmentation of 2D images, as well as volumetric medical data. A principle task of the segmentation is image partitioning into a set of non-overlapping regions. This package provides segmentation technique based on 2D/3D Delaunay triangulation. Triangular/tetrahedral mesh is used to partition image data into elements, while the mesh construction process respects significant image edges. Therefore, surfaces of image regions are well described and can be easily derived. To provide high quality meshes, methods like isotropic meshing and variational tetrahedral meshing can be found in the package. Finally, every element of the mesh (e.g. tetrahedron) is characterized by its feature vector detailing underlying image data. The library provides several clustering methods to classify these feature vectors into groups, image segments. Some traditional methods like region growing and merging are also present. All these techniques are modified, so that they work with meshes instead of raster image data.