Image segmentation using iterative watershed and ridge detection

Abstract

Those objects without regular boundaries and homogeneous intensities,such as metallographic images,make the conventional approaches hard to achieve a satisfactory partition.Therefore,a novel segmentation algorithm—an improved approach based on iterative watershed was presented.The seeds were selected by an effective double threshold approach,and the ridges were superimposed as the highest waterlines in the watershed transform.To tackle the over-segmentation problem,the blobs were merged iteratively with the utilization of Bayes classification rule.Experimental results show that the algorithm is effective in performing segmentation without too much parameter tuning.