The region-merging algorithm is a widely used segmentation technique for still-image segmentation. 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.
Dieser Eintrag ist Teil der Universitätsbibliographie.
Search Authors in