中文摘要：

改进LI的保持距离水平集方法，提出自适应分割弱边缘的活动轮廓模型，并证明自适应力的双向性。模型中自适应力的系数加入图像的灰度均值，根据演化曲线的位置自适应的收缩或扩张。结果表明，该方法克服了原LI模型初始轮廓必须完全包围或含在目标物体内的问题，可以任意设置初始轮廓大小及位置，能够分割多目标图像，具有较强的抗噪性。

英文摘要：

An adaptive active contour model for weak boundary extraction was proposed to improve LI＇s distance preser- ving level set method. Besides, the adaptive force was proved to be bi-directional. The mean gray value of the image was added in the coefficient of the proposed model, so that the adaptive force could shrink or expand adaptively accord- ing to the position of the evolution curve. The experimental results showed that the proposed method could overcome the problem of LI＇s model, which was that the initial contour must be fully enclosed by or contained within the target object. It was robust with the position of the initial contour and noise, and could segment multi-target images.