Image Segmentation Based On Partial Differential Equation

Image segmentation is one of the essential problems in the field of image processing, which has been receiving broad attentions. The target of images segmentation is to isolate the interested objects from an image and get the boundaries of the objects. There are great deals of researches on how to detect the objects in an image in the fields of Medicine, Military and Industry quickly and accurately. Recently years, image segmentations based on partial differential equation (PDE), which is one of the novel and efficient segmentation ways, are gradually turned into research hotspot. In this dissertation, we discuss based-PDE image segmentation problems, which will solve the drawbacks of long evolving time and boundary leaking in geometric active contour (GAC) models.In based-PDE image segmentation, GAC models are applied extensively to computer vision and image analysis, particularly to locate object boundaries. GAC-based segmentations have the change flexibility of topological structure; however, they have the drawbacks of long evolving time and boundary leaking. Because halting speed fields (HSF) in GAC models are typically not smooth enough in homogenous region, they are not able to make the active contour quickly move towards the desired object boundaries. On the other hand, the HSF don't really vanish along the object boundaries, thus the curve propagating can not stop on the object boundaries and continuously go across the object boundaries (boundary leaking). In this dissertation, an anisotropic diffusion model and multi-scale diffusion are therefore proposed and then applied to the HSF in GAC model. This GAC-based segmentation with the diffused HSF can overcome the two drawbacks above. Experimental results show improvements in terms of reducing both segmentation time and boundary leaking, in comparison with GAC model with the original HSF.