高斯拟合亚像素边缘检测算法.pdfVIP

第 31卷第 1期 计算机应用 Vo.l 31No. 1 2011年 1月 Journal ofComputerApplications Jan. 2011 : 1001- 9081( 2011) 01- 0179- 03 do:i 10. 3724/SP. J. 1087. 2011. 00179 尚雅层, 陈 静, 田军委 ( , 710032) (hailingmm 123 163. com) :针对传统边缘检测算法的定位精度低对噪声敏感等缺点, 出基于函数曲线拟合的亚像素边缘检测算 法 梯度方向高斯曲线拟合亚像素定位算法该方法首先在边缘附近选取 一系列点, 求得这些点的灰度值, 进而 求得这些点的梯度值,然后运用高斯曲线来对这些点的梯度值进行拟合, 最后通过拟合曲线求得高斯曲线的对称轴 位置即为亚像素位置实验表明该算法能够很好地实现亚像素定位, 通过与其他两种亚像素定位算法的比较, 得出 该算法运行时间较短,效率较高 : 图像处理; 亚像素;边缘检测; 高斯拟合; 最小二乘法 : TP391. 41 : A Subp ixel edge detection algorithm based on Gau ss fitting SHANG Yaceng, CHEN Jing, TIAN Junwei (School of M echatronicE ng ineering, X ian Technolog ical University, X ian Shaanxi 710032, China) A bstract: Concerning the low accuracy in localization and sensitivity to noise in traditional edge detection algorithms, a subpixel edge detection algorithm based on function curve fitting, Gauss fitting of gradient direction subpixel edge detection algorithm was proposed. Thismethod firstly chosed a series of points near the edge, then got the grey level of these points, and then tried to get the gradient level of these points. Then Gauss curveswere used to fit thegradient levels of these points. Finally the axis of theGauss curves was got by fitting, and the position of axis would be the subpixel edge position. The expermi ental results show that this algorithm can localize the subpixel edge position accurately. The comparision w ith other two algorithms shows that the running tmi e of this algorithm is shorter, and the efficiency is relativelyhigher. K ey w ords: mi age processing; subpixel; edge detection; Gauss