首页> 外文会议>IEEE particle accelerator conference >Representation, classification and modelling of graphs forefficient pattern recognition in line images
【24h】

Representation, classification and modelling of graphs forefficient pattern recognition in line images

机译:图形的表示,分类和建模线图像中的有效模式识别

获取原文

摘要

Improvement of graph matching by a start condition parser isdiscussed, which arranges the dynamic lists into a hierarchical treestructure, using general topological criteria. The reference graphs ofthe symbols are generated by another parser, which interprets a modeldescription language. Applications are in the processing of technicaldrawings. For example, in a circuit diagram, component symbols would berecognised and treated separately from connecting lines. The performancegain over known algorithms exceeds a factor of about ten in experimentalresults
机译:启动条件解析器对图形匹配的改进是 讨论,将动态列表排列到分层树中 结构,使用一般拓扑标准。参考图 这些符号是由另一个解析器生成的,解析器对模型进行解释 描述语言。应用程序在技术处理中 图纸。例如,在电路图中,组件符号应为 与连接线分开识别和处理。表现 实验中,相对于已知算法的增益超过了大约十倍 结果

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号