基于小波变换的多尺度图象边缘检测  

Image Edge Detection Based on Multiscale Wavelet Transform

作　　者：张林[1] 钟伯成[1] 王颖[1] 储忠[1] 

机构地区：[1]合肥学院计算机信息系,安徽合肥230022

出　　处：《合肥学院学报（自然科学版）》2004年第2期7-9,共3页Journal of Hefei University :Natural Sciences

摘　　要：提出了一种新的图象边缘检测方法,这种方法解决了第一代多尺度边缘检测方法中存在的两个问题,即边缘仅定义为信号的奇异性表现和滤波尺度参数难以选择。实验结果表明,本方法和传统的边缘检测算法相比具有定位精度高,去噪效果好等明显的优点。A new image edge detection method has been presented in this paper. It solve the two problem that existed in the first generation wavelet transform, one is edge define only considering its oddity, another is to select filtering scale difficultly. Experimental results indicate the algorithm provides higher precision and signal-to-noise-ratio compared with classical methods of edge detection.

关 键 词：数字图象处理 小波变换 多尺度 图象边缘检测 算法 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]