In this paper, a general method for meta-graph recognition is proposed based on curve fitting and separation of line and smooth curve.
本文针对图纸矢量化中的图元识别技术，提出了系统的基于线弧分离和拟合识别方法。
Based on the research of existing rules, a new method for the FPC line defect recognition is advanced, named multi-template reference contrast.
该文针对FPC线路的瑕疵识别问题， 在研究已有瑕疵识别规则的基础上， 设计了一种多模板参考比对法。
This paper puts forwards a method for automatically generating line based on the recognition of arrow symbol.
提出了一种基于图形箭头符号识别的直线图形自动生成方法。
应用推荐