基于多特征和模糊推理的边缘检测

Edge Detection Using Multiple Edge Features and Fuzzy Reasoning

图像边缘检测的传统方法一般仅基于边缘邻域的一阶或二阶导数这一单一特征 ,并且对模糊边缘图像不敏感 ,针对此问题 ,本文提出基于多特征和模糊推理的边缘检测算法 .根据不同类别的边缘点附近灰度分布的特点定义多种边缘特征 ;利用不同的边缘特征确定模糊规则 ,用min max重心法模糊推理该点的边缘隶属度 ,实现边缘检测 .最后 ,文中给出应用本算法进行边缘检测的实例 ,与传统算法相比较 ,本算法检测边缘效果更好 ,并能较好地抑制噪声 .

This paper gives a method of image edge detection,using multiple edge features and fuzzy reasoning.To effectively extract edges,edge pixels are classified according to the difference of intensity distribution,and multiple effective edge features are defined.Edges are detected by applying fuzzy reasoning (min max centriod method),based on local image edge characteristics.Finally,the given algorithm is tested on several images.Comparison is made with standard edge detection techniques.