中文摘要：

提出了一种由测地线活动轮廓模型GAC（Geodesic Active Contour）和局部区域信息相结合的图像分割新方法LGAC（Local Geodesic Active Contour）。构造了基于图像局部信息的演化曲线符号压力函数和演化模型,用水平集方法演化实现,零水平集能准确地在目标边缘收敛,对目标背景对比度较低的图像的分割达到理想效果。利用高斯核函数对水平集函数平滑处理以维持演化稳定,节省了计算时间。实验结果证明了该方法的可行性。

英文摘要：

This paper proposes a novel method of image segmentation,LGAC（Local Geodesic Active Contour）.It is based on the combination of the model of geodesic active contour with the local area information.The sign pressure function of the evolution curve based on the local area and the new evolution model are constructed.The method is implemented by the level set and the zero level set can converge in the boundary accurately.This method can achieve ideal effect for image segmentation of low contrast.The paper adopts Gaussian kernel function to regulate the level set for its smoothness and stability which saves computing time.The experimental results confirm the feasibility.