小波边缘分布及边缘融和算法研究  

Edge Distribution of Wavelet Transform and Edge Fusion Algorithm

作　　者：万月亮[1] 曹元大[1] 李钝[1] 

机构地区：[1]北京理工大学计算机科学技术学院,北京100081

出　　处：《小型微型计算机系统》2008年第7期1308-1313,共6页Journal of Chinese Computer Systems

基　　金：总装备部"十五"预研项目(413150801)资助

摘　　要：小波变换是图像边缘检测的重要算法之一,为了综合大尺度下边缘抗受噪声强和小尺度下边缘定位准确的优点,提出一种基于多尺度小波边缘分布的边缘检测算法.研究小波边缘检测中的边缘分布,提出有效边缘包络带,讨论了不同类型边缘包络带的有效范围;在有效边缘包络带内采用融和算法进行边缘检测.对合成和自然图像的试验表明算法的有效性.Edge detection based on multi-scale wavelet transform is one of the important algorithms in images edge detection. In large scale it is strongly anti-noise, and in small scale it can accurately locate edge. In order to give attention to both, a new edge detection method base on edge distribution of multi-scale wavelet transform is developed. Firstly, edge distribution of wavelet edge detection is discussed, the effective edge envelope of different edge models based on compact symmetry and smooth function were discussed. Secondly, in the range Of effective envelope of different edge model, an edge detection based fusion is adopted for local edge of different scale edge fields. The validity of the algorithm is proved by experiment for artificial and real images.

关 键 词：小波变换 边缘分布 边缘融和 有限元 

分 类 号：TN391.41[电子电信—物理电子学]