引用本文:钱迎雪,黄石生,周其节.应用ART2人工神经网络自组织形成焊缝图象中的典型空间模式[J].控制理论与应用,1994,11(6):720~727.[点击复制]
QIAN Yingxue, HUANG Shisheng and ZHOU Qijie.The Self-Organization of Typical Space Patterns in Welding Seam Tracking Image by Using ART2 Artificial Neural Networks[J].Control Theory and Technology,1994,11(6):720~727.[点击复制]
应用ART2人工神经网络自组织形成焊缝图象中的典型空间模式
The Self-Organization of Typical Space Patterns in Welding Seam Tracking Image by Using ART2 Artificial Neural Networks
摘要点击 725  全文点击 409  投稿时间：1993-02-11  修订日期：1994-07-07
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  
  1994,11(6):720-727
中文关键词  模式识别  人工神经网络  焊缝视觉跟踪
英文关键词  pattern recognition  artificial neural networks  welding seam tracking
基金项目  
作者单位
钱迎雪,黄石生,周其节 华南理工大学机械工程二系 
中文摘要
      应用ART2人工神经网络算法，使采集到的焊缝横截面方向上的灰度分布数据自组织形成若干种空间模式，并把它们作为典型空间模式存储在ART2人工神经网络的LTM中。对实时采样到的灰度分布进行空间模式匹配程度检验，根据模式分布情况确定出焊缝位置。文中对梯度法检测结果进行了分析和比较，结果表明基于ART2人工神经网络的焊缝位置检测方法具有更强的噪声抑制能力，因而检测结果更准确、可靠。
英文摘要
      The algorithm based on the ART2 artificial neural networks is used to self-organize the grey level distribution data in the transversal direction of a welding seam and forms several typical space patterns and stores them in the LTM (long time memory) of the ART2 artificial neural networks. Then the grey level distribution data of a welding image obtained in real time is matched with these typical space patterns. The welding seam position can be determined according to the situation of pattern distributions. It is shown that this method can inhibit strong noises and work correctly in a very noisy circumstance.