Image segmentation is defined as partitioning an image into non-overlapping regions based on the intensity or texture. The active contour methods pro-vide an effective way for segmentation, in which the boundary of an object (usually with large image gradient value) is detected by an evolving curve. However, these methods have limitations due to the fact that real images may have objects with complex geometric structures and shapes, and are often corrupted by noise. Developing more robust and accurate active con-tour methods has been an active research area since the idea of the methods was proposed. In this thesis, we propose a new active contour method and apply the method to medical image segmentation. This new method uses a long-ranged interaction between image boundaries and the mo...[ Read more ]

Image segmentation is defined as partitioning an image into non-overlapping regions based on the intensity or texture. The active contour methods pro-vide an effective way for segmentation, in which the boundary of an object (usually with large image gradient value) is detected by an evolving curve. However, these methods have limitations due to the fact that real images may have objects with complex geometric structures and shapes, and are often corrupted by noise. Developing more robust and accurate active con-tour methods has been an active research area since the idea of the methods was proposed. In this thesis, we propose a new active contour method and apply the method to medical image segmentation. This new method uses a long-ranged interaction between image boundaries and the moving curves, which is inspired by the elastic interaction between line defects in solids (dislocations). The new method is more efficient and effective, especially in detecting thin, weak and blurred structures such as the images of blood vessels, as compared with the other edge based methods.