针对图像分割中经典GAC模型无法准确分割拓扑结构变化的凹陷目标、容易穿越深度凹陷的弱边缘轮廓和无法准确分割含噪声目标的问题, 通过利用图像灰色关联度、类间方差和经典GAC模型构造新能量函数, 提出了一种改进的GAC模型, 该模型可增强经典GAC模型的边界检测能力, 减少分割时间。仿真实验验证了改进的GAC模型的正确性和有效性。

The problems of mismatching weak edge,topology change of target structures and sensitive to noise in traditional active contour model are studied, by combining Ostu algorithm,grey relational analysis of image with traditional GAC model, an improved model is proposed. In this way,the detecting boundary ability of traditional GAC model is enhanced.Simulation results show that the proposed model can obtain better results with respect to images and significantly reducing segmentation time.A large number of comparing experiments demonstrate the superior performance of the proposed method.