Combining region splitting and edge detection through guided Delaunay image subdivision

In this paper, an adaptive split-and-merge segmentation method is proposed. The splitting phase of the algorithm employs the incremental Delaunay triangulation competent of forming grid edges of arbitrary orientation, and position. The tessellation grid, defined by the Delaunay triangulation, is adjusted to the semantics of the image data by combining similarity and difference information among pixels. Experimental results on synthetic images show that the method is robust to different object edge orientations, partially weak object edges and very noisy homogeneous regions. Experiments on a real image indicate that the method yields good segmentation results even when there is a quadratic sloping of intensities particularly suited for segmenting natural scenes of man-made objects.