常用边缘检测算法的定量比较  

Quantitative Comparison of Common Edge Detection Algorithms

作　　者：陈彦燕[1] 王元庆[1] 

机构地区：[1]南京大学电子科学与工程系,南京210093

出　　处：《计算机工程》2008年第17期202-204,共3页Computer Engineering

基　　金：国家自然科学基金资助项目(60472026)

摘　　要：在总体定性分析的基础上,根据边缘连通度、抗噪性能、运算复杂度等典型的边缘检测算法性能标准,利用定量计算结果比较并验证各种边缘特征提取算法的优缺点。采用B样条三次曲线对原始图像进行拟合,显著提高了检测后的图像质量。实验结果表明,该方法可以很好地应用于图像处理领域。Based on whole qualitative analysis, this paper compares and validates merits and demerits of various edge detection algorithms in a qnantificational way from several typical judgement standards for edge detection algorithms like edge connectivity, nosie resistence ability, operation complexity. By means of B cubic spline interpolation, it improves the quality of the detected images. Experiental results show that this methods can be well applied in the region of image processing.

关 键 词：边缘检测 边缘连通度 频谱图 三次样条插值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]