电子学报 ›› 2012, Vol. 40 ›› Issue (11): 2221-2225.DOI: 10.3969/j.issn.0372-2112.2012.11.013

• 学术论文 • 上一篇    下一篇

基于脉冲耦合神经网络的点云曲面去噪

邹北骥1, 周浩宇1, 辛国江1, 谭光华2, 陈再良1   

  1. 1. 中南大学信息科学与工程学院,湖南长沙 410083;
    2. 湖南大学信息科学与工程学院,湖南长沙 410082
  • 收稿日期:2011-12-17 修回日期:2012-04-29 出版日期:2012-11-25
    • 作者简介:
    • 邹北骥 男,1961年生于湖南邵阳,博士,教授,博士生导师.分别于1982年、1984年和2001年在浙江大学、清华大学和湖南大学获得工学学士、工学硕士和工学博士学位.现为中南大学信息科学与工程学院副院长.主要研究方向:计算机视觉、机器学习、虚拟现实技术、计算机图形学、数字图像处理、CAD技术及软件工程技术. 周浩宇 男,1979年生于湖南长沙,博士研究生.分别于2002年和2005年在湖南大学获得工学学士和工学硕士学位.现就读于中南大学信息科学与工程学院.研究方向:计算机图形图像处理. E-mail:zhou_haoyu@163.com
    • 基金资助:
    • 国家自然科学基金 (No.60970098,No.60803024,No.60903136,No.61173122); 国家自然科学基金重大研究计划 (No.90715043)

PCNN-Based Point Set Surface Denoising

ZOU Bei-ji1, ZHOU Hao-yu1, XIN Guo-jiang1, TAN Guang-hua2, CHEN Zai-liang1   

  1. 1. School of Information Science and Engineering Central South University,Changsha,Hunan 410083,China;
    2. College of Information Science and Engineering Hunan University,Changsha,Hunan 410082,China
  • Received:2011-12-17 Revised:2012-04-29 Online:2012-11-25 Published:2012-11-25
    • Supported by:
    • National Natural Science Foundation of China (No.60970098, No.60803024, No.60903136, No.61173122); Major Research Project of National Natural Science Foundation of China (No.90715043)

摘要: 提出一种基于脉冲耦合神经网络(PCNN)的点云曲面去噪算法.该算法主要分为两步:噪声点定位和噪声点滤波.首先针对点云曲面构建一个PCNN神经网络,各个神经元的外部刺激值由邻近点的几何位置差异和法向差异构成,利用神经元输出的自适应点火捕获特性,实现了噪声点的定位;而后针对点云曲面中的噪声点,基于网格光顺中双边滤波的思想,实现噪声点的滤波,对于非噪声点,则保持原有的几何位置不变.实验结果表明,由于区分了噪声点和非噪声点,该算法较传统的点云曲面去噪算法能更加有效的去除噪声的同时并保持模型的几何特征.

关键词: 点云曲面, 点云曲面去噪, 脉冲耦合神经网络, 双边滤波

Abstract: A novel algorithm of PCNN-based point set surface denoising is proposed in this paper.The algorithm mainly includes two steps:location of noise points and smoothing of the located noise points.Firstly,a pulse-coupled neural network for the point set surface is constructed.The stimulation value of each neuron is decided by the differences of the position and the normal of the k-nearest neighbor points.The noise points are located through the adaptive firing capture feature of the PCNN.Based on the idea of bilateral filtering,the located noise points are smoothed,while the non-noise points remain their geometry position.Due to the different operations on noise points and non-noise points,experiments show that our algorithm performs better to remove the noise of the point set surface while keeping the features of the model.

Key words: point set surface, point set surface denoising, PCNN, bilateral filtering

中图分类号: