An Algorithm of Image Segmentation Based on Fuzzy Mathematical Morphology

The paper discussed a new image segmentation algorithm that based on fuzzy mathematical morphology, aiming at the noise and exiguity catchment basin of image that result in over-segmentation phenomenon when adopt traditional watershed algorithm to segment an image. The method adopted firstly opening-closing algorithm based on fuzzy mathematical morphology to smooth the image and then to compute its gradient operators based on basic morphology. Furthermore, the method segmented the gradient image based on fuzzy mathematical morphology to get the result. The simulation experiment result showed that it not only can eliminate over-segmentation phenomenon that resulted from traditional mathematical morphology segmentation algorithm, realize goal full segmentation from background, but also can save image detail perfectly when using the new image segmentation algorithm based on fuzzy mathematical morphology of segment image.