Multi-Stage Region Merging for Image Segmentation
Thomas Brox, Dirk Farin · TU/e Research Portal · 2001
This paper evaluates the properties of several merging criteria when applied to real-world images. These criteria properties have been exploited to develop a novel algorithm, which is a multi-stage generalization of conventional region merging. The new algorithm uses a sequence of different criteria to achieve a semantically and subjectively superior segmentation result