一种改进的模糊边缘检测快速算法  

An Improved Fast Edge Detection Algorithm Based on Fuzzy Sets

作　　者：刘金华[1] 唐竞新[1] 龙图景[1] 

机构地区：[1]清华大学自动化系,北京100084

出　　处：《系统仿真学报》2003年第2期273-274,297,共3页Journal of System Simulation

摘　　要：系统分析了Pal.King模糊边缘检测算法的缺陷,提出了一种新的快速模糊边缘检测算法。该算法不仅克服了Pal.King模糊检测算法定义的不足,简化了复杂的变换和逆变换运算,而且针对Pal.King算法中对隶属度阈值设置为固定值的不足,提出了确定模糊增强变换中最佳隶属度阈值的自动算法。仿真结果证明,该算法效率高、提取边缘精细、适用面广,是一种很有实用价值的图象处理算法。In this paper, a novel improved algorithm based on fuzzy sets is presented by analyzing Pal.King algorithm synthetically. The algorithm presented by this paper overcomes the definition defects of Pal.King algorithm, simplifies the complex transformation calculation and presents a roboticized algorithm which determines the optical threshold value of membership, which is set stably by Pal.King algorithm. The experiment indicates that the algorithm is an efficient, pervasive and very valuable image processing algorithm which can extract general edge.

关 键 词：模糊边缘检测快速算法 边缘检测 模糊集 隶属函数 图象处理 图象分析 计算机视觉 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]