中文摘要：

将变分水平集和图像阀值化两种图像分割方法相结合,在分析灰度图像直方图分布的基础上提出利用图像阈值设定C-V模型的初始化轮廓的新方法,改变了原有C-V模型的初始轮廓线设置中存在的不足.新方法应用于牙菌斑图像分割中能够较好的识别牙齿图像边缘信息,为下一步对牙菌斑进行量化分析提供了良好的数据基础.

英文摘要：

Variational level set method is a quite hot research point in image processing.C-V model is a classic approach to segment image based on variational level set.It is especially helpful for medical images analysis,which has complex topology constructions,strong noises and lower contrast.But C-V model depends on initial contour.Image thresholding is also a simple and popular image segmentation method,which separates an image into two parts,and gets the target sub-image from background image.In the article,these two methods are integrated together.By analyzing the distribution of image gray level histogram,the authors propose a new method which initializes contour using threshold.It solves the shortages about how to set initial contours in C-V model.The novel C-V model used in dental plaque image segmentation and experiments illustrates that the method proposed can help segment images.It provides a preliminary work to further analyze dental plaque.