Cell Image Segmentation Based on an Improved Watershed Transformation

This paper presents an improved watershed segmentation method based on multi-scale edge detection which is applied to cell image segmentation. First, advantage of using morphology for the edge detection is discussed, secondly, multi-scale edge detection method is constructed by the weighted combination of morphological operations. After using the multi-scale edge detection method, result is taken as the input of watershed segmentation, then implements region merging to get the final result. Experimental results show that the method can provide precise and closed region contour.