Normalized cuts and watersheds for image segmentation

In this paper problem of image segmentation is considered. Specifically, normalized graph cut algorithm is regarded. In its source version the Ncut approach is computationally complex and time consuming, what decreases possibilities of its application in practical applications of machine vision. The segmentation approach proposed in this paper overcomes these limitations by incorporating watershed transform and normalized cuts. Results of the proposed method are presented, compared with results of the original normalized cut method and discussed.