基于自适应滤波的单像素宽形态学边缘检测  

One Pixel Width Morphological Edge Detection Algorithm Based on Adaptive Filter

作　　者：唐永鹤[1] 胡谋法[1] 卢焕章[1] 

机构地区：[1]国防科学技术大学ATR实验室,湖南长沙410073

出　　处：《信号处理》2011年第8期1166-1170,共5页Journal of Signal Processing

摘　　要：为了进一步提高边缘检测算法的抗噪性和定位精度,提出了一种基于自适应滤波的单像素宽形态学边缘检测算法。首先,分别对图像进行中值滤波和加权均值滤波,并通过自适应调整中值滤波结果和加权均值滤波结果所占的权重抑制脉冲噪声和高斯噪声。然后根据不同取向的结构元素可以有效地检测出不同走向的边缘细节这一特性,定义了一种具有方向估计的形态学梯度,并利用其检测图像的边缘,最后沿梯度方向进行非极大值抑制以获取单像素宽边缘。实验结果表明,本文算法不仅能够准确地检测图像边缘,而且具有较好的抗噪性能,处理速度也较快。In order to improve the noise immunity and accuracy of edge detection algorithm,a one pixel width morphological edge detection algorithm based on adaptive filter is presented.First,the image is filtered with median filter and weighted average filter respectively.Pulse noise and Gaussian noise are suppressed by adjusting the weighted value of median filter results and weighted average filter results adaptively.Then,a morphological gradient with orientation was defined on the basis of that it is able to detect edges with different direction when using structure elements with different tropism,and the gradient is used to extract image edge which is thinned with one pixel width by implementing non-maxima suppression along the orientation of the gradient finally.Simulation results indicate that the proposed algorithm is not only able to detect edge accurately,but also has better noise immunity and faster processing speed.

关 键 词：边缘检测 自适应滤波 结构元素 非极大值抑制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]