Fast Active Contours Model for Image Segmentation: A Review of Recent Trends
Huimin Lu, Yujie Li, Shiyuan Yang, Seiichi Serikawa · Journal of the Institute of Industrial Applications Engineers · 2013
As we all known, the stand-of-the-art active contours model (ACM) methods can segment the objects actually. However, most of them are very time-consuming and inefficient. In this paper, we review most of recent ACM algorithms, and propose a new model, which is based on the techniques of piecewise constant and piecewise smooth Chan-Vese model (PC/PS) and semi-implicit additive operator splitting (AOS) scheme. Different from traditional models, our model is corresponding to a new signed pressure force (SPF) function, which can efficiently stop the contours at weak or blurred edges. It can not only ensure the smoothness of the level set function, but also speed up the computational complexity of re-initialization. Numerical synthetic and real images demonstrate the advantages of the proposed method over geodesic active contour (GAC), piecewise constant (PC) model, and piecewise smooth (PS) model.