基于二维EMD改进方法的图像边缘检测  

Image edge detection based on two-dimensional EMD improved method

作　　者：赵晨[1] 周振国[2] 崔颖[2] 

机构地区：[1]哈尔滨工程大学水声工程学院,哈尔滨150001 [2]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《黑龙江大学工程学报》2012年第3期106-110,共5页Journal of Engineering of Heilongjiang University

基　　金：国家自然科学基金项目(61077079;60802059);高等学校博士学科点专项基金(20102304110013)

摘　　要：图像边缘检测在图像处理与分析中具有重要作用,常用的多尺度多分辨率边缘提取方法主要有小波变换和经验模式分解法。针对传统的二维经验模式分解过程复杂,边界效应抑制效果不明显等问题,提出了一种易于实现的二维经验模式分解改进方法,并采用该方法结合灰度图像二值化和形态学细化操作实现图像的边缘检测。实验结果表明,该检测方法可以有效地提取图像的边缘信息。Image edge detection plays an important role in image processing and analysis, and wavelet transform and empirical mode decomposition are the commonly used multi-scale and multi-resolution edge extraction rnetho＆ Considering the complexity and less obviousness of the boundary effect inhibition of the traditional method, a kind of improved two-dimensional empirical mode decomposition method which is easy to implement is proposed. Com- bining the gray image binarization with morphological thinning operation, the improved two-dimensional empirical mode decomposition method is used to achieve image edge detection. The experimental results show that the detection method can effectively extract the image edge information.

关 键 词：图像边缘检测 多尺度分析 边界效应抑制 二维经验模式分解 形态学细化 

分 类 号：TN911.7[电子电信—通信与信息系统]