Extracting Regions of Interest Applying a Local Watershed Transformation

In this paper, we present a new technique for extracting regions ofinterest (ROI) applying a local watershed transformation. The proposedstrategy for computing catchment basins in a given region ofinterest is based on a rain-falling simulation. Unlike the standardwatershed algorithms, which flood the complete (gradient magnitudeof an) image, the proposed approach allows us to perform thistask locally. Thus, a controlled region growth is performed, savingtime and reducing the memory requirement especially when appliedon volume data.A second problem arising from the standard watershed transformationis the over-segmented result and the lack of sound criteriafor merging the computed basins. For overcoming this drawback,we present a basin-merging strategy introducing four criteria formerging adjacent basins. The threshold values applied in this strategyare derived from the user input and match rather the attributesof the selected object than of all objects in the image. In doing so,the user is not required to adjust abstract numbers, but to simply selecta coarse region of interest. Moreover, the proposed algorithmis not limited to the 2D case. As we show in this work, it is suitablefor volume data processing as well. Finally, we present the resultsof applying the proposed approach on several example images andvolume data sets.