基于单义域邻接图的工程图纸扫描图像的字符提取

工程图纸扫描图像的图文分割是一个重要问题。本文在构建单义域邻接图基础上来提取字符及其特征。图文分离先从单义域中筛选字符笔画域，进行初步分离。然后，以字符笔画域为起点，遍历邻接图来搜索邻接字符笔画域提取字符域，分析特性作进上步筛选。以字符域邻近与共线为判据来组合字符串域，字符域，分析特性作进上步筛选。以字符域邻近与共线为判据来组合字符串域，字符域邻近是用其外接膨胀矩形相交来判定。利用共串字符域外接矩

AN ALGORITHM OF EXTRACTING CHARACTERS FROM SCANNED IMAGE OF ENGINEERING DRAWINGS USING PRIMITIVE REGION ADJACENCY GRAPH

It is a important issue how to separate text from scanned image of engineenng drawings. Thepaper presents an algorithm to extract characters and their fetures from images using PrimitiveRegion Adjacency Graph. We can easily get character stroke regions from primitive regions. At startof a character stroke region. a character region grows by traversing the graph for adjacent characterstroke regions. Afer analyzing features of character regions, we can get real character regions. Astring can be got through combining those near and collinear character regions. If rectangles inflatedof two character regions are intersected, they are near. The direction of a string region is attained bythe center points of enclosed rectangles of characters shared by the string and figures attached. Thencharacters not horizontal are rotated to horizontal. A Primitive Region Adjacency Graph canrepresent geometrical and topological features of a character region, which is helpful to Cxtractfeatures of a character region. Some applications show that the algorithm can deal with adherence ofcharacters to graphics, and is effective and robust.