基于知识的窗口矢量化技术  

Technique of Knowledge-Based Window Vectorization

作　　者：谭柏珠[1] 叶邦彦[1] 陈澄洲[1] 

机构地区：[1]华南理工大学机电工程系,广州510640

出　　处：《计算机辅助设计与图形学学报》2000年第2期105-109,共5页Journal of Computer-Aided Design & Computer Graphics

摘　　要：介绍了一种工程图扫描识别中基于知识库推理的自适应窗口矢量化技术.它既避免了常用的基于细化的识别处理方法在交叉点处引起的畸变,又较好地实现了交叉点的精确定位.文中还给出了自适应窗口的约束条件和黑游程结构图的构造方法,同时详尽地分析了知识库的组织机制.Vectorization is a key issue in the process of recreating engineering drawings from scanned input image. This paper introduces the technique of adaptive window vectorization based on knowledge base inference. It not only avoids distortion caused by the commonly used thinning based recognition process at cross point, but also achieves the accurate positioning of cross point. The constraint conditions of adaptive window and the approach of constructing black run length structure drawing are also given. Besides,the organization mechanism of knowledge base is analysed in detail.

关 键 词：知识库 自适应窗口 矢量化 工程图 自动识别 

分 类 号：TB23[一般工业技术—工程设计测绘] TP391.41[自动化与计算机技术—计算机应用技术]