改进的水平集方法及其在图像分割中的应用

Improved Level Set Method and Its Application to Image Segmentation

为了稳定水平集函数的演化过程,提出了一种改进的距离规则化水平集方法,新方法与传统的距离规则化方法相比,能更好地维持水平集函数的符号距离函数特性.为了检验新方法的性能,首先将其应用到基于边缘的主动轮廓模型中并用于图像分割,实验结果表明新方法能有效提高分割效率和精度.同时,还将新方法应用到一种改进的基于区域的主动轮廓模型中,实验结果不仅进一步验证了新方法的有效性,还表明新方法能改善初始位置的鲁棒性.

To stabilize the level set function of evolution,this article puts forward an improved level set method.The new method can keep the peculiarities of signed distance function compared with the distance regulation level set evolution method.To verify the performance of the new method,it is applied to the active contour model based on edge and used for image segmentation.The experimental results show that the improved level set evolution method can improve the segmentation efficiency and segmentation accuracy greatly.At the same time,the new method is applied to an improved region-based active contour model.The experimental results not only verify the validity of the new method,but also show that the new method can improve the robustness of the initial position.