基于小波变换的屋脊边缘亚像素检测  

Sub-pixel roof edge detection based on wavelet transform

作　　者：丁兴号[1] 邓善熙[2] 

机构地区：[1]厦门大学电子工程系,福建厦门361005 [2]合肥工业大学仪器仪表学院,安徽合肥230009

出　　处：《哈尔滨工业大学学报》2004年第11期1480-1482,1530,共4页Journal of Harbin Institute of Technology

基　　金：安徽省"十五"科技攻关重点项目(01022010).

摘　　要：工业图像检测中,许多待检目标边缘是屋脊边缘,而现有亚像素边缘检测算法都是假设边缘模型为阶跃边缘,并且现有算法在定位精度、抗噪性能和计算速度方面还不尽人意.针对上述问题,提出一种使用小波变换系数的屋脊边缘亚像素检测算法,将小波分析和概率统计理论引入到亚像素边缘检测问题中.该方法具有较好的定位精确度、抗噪能力和较快的计算速度.实验证明该方法可达到1/60像素的精确度.In the traditional algorithms for sub-pixel edge detection, the model of edges on the objects images is supposed as a step edge. However, the edges of many industrial objects inspected are roof edge. For improving the traditional algorithms in edge location accuracy, ability of anti-noise and the computation speed, a sub-pixel roof edge detection algorithm is presented, based on wavelet transform coefficient and probability theory. This algorithm is shown with better edge location accuracy, anti-noise ability and low computation cost. The experiment showed that the measurement precision reached 1/60 pixel.

关 键 词：小波变换 屋脊边缘 亚像素 边缘检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]