A novel method of image segmentation using watershed transformation

Watershed segmentation has recently become a popular tool for image segmentation. However, its use for automatic image segmentation has been limited particularly due to over-segmentation and sensitivity to noise. This paper presents a new method of image segmentation using watershed transformation. To use morphological opening and closing operations to process the gradient image aim to eliminate the over-segmentation areas, and reconstruction of the morphological gradient can maitain the shape of gradient image. The proposed method can simplify gradient image while maintaining the contours of the exact location of the dividing line, eliminating the root causes of the phenomenon have been split. Simulation experimental results show the proposed approach has better segmentation results than the traditional method in terms of visual effects division or eliminate over-segmentation, regional profile and anti-noise performance positioning side surface.