为了进一步提高C-V模型的分割速度、降低初始轮廓曲线位置对分割结果的耦合性, 提高多光谱成像仪图像分割效率, 本文提出一种改进的C-V模型。该模型通过将每次迭代得到的距离函数的最大值引入C-V模型的Dirac函数, 对该函数进行自适应参数修正, 以拓宽活动轮廓线的有效作用范围, 进而大大降低分割算法的迭代次数。实验结果表明, 与经典的C-V模型相比, 改进的C-V模型在其终止条件下得到了较理想的分割效果, 降低了初始曲线位置对最终分割结果的影响, 且新模型的收敛速度在原有的基础上至少提高了7倍。改进的C-V模型在实时性及全局性方面都得到了明显改进, 进一步提高了该算法在多光谱成像仪的图像分割方面的鲁棒性。

In order to improve the image segmentation speed when using C-V model, reduce the segmentation coupling with initial contour position, and improve the image segmentation efficiency of multi-spectral imager, an improved C-V model is proposed in the paper. In this model, the Dirac function′ parameter is corrected adaptively by introducing the maximum value of distance function in each iteration. In this way, the effective range of active contour is broadened, and the number of iterations is reduced. The experimental results show that the ideal segmentation effect is obtained by the improved C-V model with the iteration termination condition. Compared with the classic C-V model, the influence of initial contour position on segmentation is reduced. In addition, the convergence speed is improved by 7 times. The characteristics of real time and global nature both become better. Therefore, the robustness of multi-spectral imager segmentation is improved accordingly.