Region-based Active Contour Segmentation Model with Local Discriminant Criterion

This paper presents a novel region-based active contour model for image segmentation in a variational level set formulation. We define a local discriminant criterion on the basis of the global and local region-based active contour model. The objective function in this model is thereafter minimized via level set method. By introducing the local discriminant criterion to separate background and foreground in local regions, our model not only achieves accurate segmentation results, but also is robust to initialization. Extensive experiments are reported to demonstrate that our method holds higher segmentation accuracy and more initialization robustness, compared with the global region-based and local region-based methods. Experimental results for synthetic images and real medical images show desirable performances of our method.