二维直方图模糊边缘检测算法

2-D Histogram Fuzzy Edge Detection Algorithm

为了提高一般模糊边缘检测算法的抗噪声能力,本文提出了一种二维直方图模糊边缘检测算法。该方法通过像素邻域信息构建二维直方图,采用二维Otsu的方法来确定阈值向量,根据阈值向量重新定义了模糊隶属度函数;另外本文结合量子遗传算法来快速搜索阈值向量,大大节省了时间。仿真实验表明,该方法边缘检测效果较好,同时具有更强的抗噪声性能。

In order to improve noise immunity of general fuzzy edge detection algorithm,this paper presents a two-dimensional histogram fuzzy edge detection algorithm.The method constructs a two-dimensional histogram through pixel neighborhood information and obtains the threshold vector by 2-D Otsu.Then it redefines the membership function according threshold vector.Moreover,the method combines QGA to quickly search the threshold vector,saving a lot of time.Simulation results show that this method can obtain a better edge detection effect,and also has a stronger anti-noise performance at the same time.