基于最小能量的图像分割方法

Image segmentation method based on minimum energy

提出了一种图像分割新方法，与 Ｓｎａｋｅ 模型一样，该方法融合了传统的三阶段分割方法，并克服了 Ｓｎａｋｅ 模型只能处理单区域轮廓线的缺陷，适用于多区域、多空间位置关系的图像分割，无需轮廓线的初始位置设定。同时，动态规划的嵌入特性，保证了图像分割的全局最优化，实现了图像轮廓线的精确定位和自动分割。实验结果表明了该方法对于多区域图像分割的有效性。

A new image segmentation algorithm is proposed in this paper. It fuses three stages of traditional image segmentation as same as Snake model does. While Snake model can only deal with single contour, this method can be adopted to multi\|objects and multi\|spatial relations. The global optimization is realized by dynamical programming and its embedding property, so that automatic segmentation and precise object location can be obtained. The experiment shows that the method is effective on multi\|objects image segmentation. \;