提出一种融合视觉感知和等周理论的图像阈值分割方法。此方法先利用人类视觉感知的特性来寻找候选阈值所在的灰度区间，然后将等周理论中的等周率作为准则从候选阈值中挑选出最佳分割阈值。在工业无损检测等一系列图像上的实验结果表明，与现有的几种经典阈值分割方法相比，本文方法的分割效果更好。

In this paper, a novel thresholding method based on human visual perception and isoperimetric theory is presented. The proposed method first utilizes characteristics of human visual perception to find a gray level interval decided by candidate thresholds, then uses isoperimetric ratio in isoperimetric theory as a criterion to determine the optimal threshold from the candidates. Experimental results on a series of images including nondestructive testing ones show that authors’ method outperforms several existing classic thresholding methods in segmentation quality.