基于SOM网络的三次B样条曲线重建.pdfVIP

192 2012 ，48 （15） Computer Engineering and Applications 计算机工程与应用 基于SOM 网络的三次B 样条曲线重建 1，2 3 王世东 ，王焕宝 WANG Shidong1，2 , WANG Huanbao3 1.安徽建筑工业学院 信息网络中心，合肥 230022 2.中国科学技术大学 火灾科学国家重点实验室，合肥 230026 3.安徽建筑工业学院 数理系，合肥 230022 1.Information Network Center, Anhui University of Architecture, Hefei 230022, China 2.State Key Lab of Fire Science, University of Science and Technology of China, Hefei 230026, China 3.Department of Mathematics, Anhui University of Architecture, Hefei 230022, China WANG Shidong, WANG Huanbao. Cubic B-spline curve reconstruction based on SOM. Computer Engineer- ing and Applications, 2012, 48 （15）：192-194. Abstract ：Curve and surface reconstruction based on unorganized data points plays an important role in the fields of reverse engineering and computer vision. This paper presents a new algorithm based on SOM to realize Cubic B-spline reconstruction. A set of unorganized data points and an initial neural network are given. The network can be optimized using the algorithm to make the neurons gradually approach the given unorganized data points and re- flects spatial characteristics of unorganized data points. Control points of cubic B-spline curve are reversely calculat- ed using the dominant points. Some experiment results show that the new algorithm is quite effective. Key words ：Self-Organizing Map（SOM）; unorganized data points; dominant points; B-spline 摘 要：使用散乱点集重建曲线曲面，在逆向工程和计算机视觉中有着广泛的应用。提出基于SOM 网络的三 次B 样条曲线重建算法。给定某一曲线散乱点集和一初始神经网络，优化SOM 网络中神经元位置，使网络逼 近散乱点和映射散乱点空间特征。用特征点反求三次B 样条曲线控制点，利用控制点重建三次B 样条曲线。 试验结果表明，算法取得的曲线重建效果良好。 关键词：自组织映射网络；散乱点；特征点；B 样条 文章编号：1002-8331（2012 ）15-0192-03 文献标识码：A 中图分类号：TP391 [2-3] 1 引言 完成的 。近年来，在逆向工程中，对特征提取问题 使用散乱点集重建曲线曲面，在逆向工程和计 的研究比较活跃。Géza Kós 等对等半径过渡特征曲