摘要
本文采用关于手绘图形基本图素的“角度和变量”与“最大距离”综合判定分类法,以流程图符为例,实现了手绘基本图形的在线机器识别.系统的识别率达94.0%~99.5%,无明显等待.
The classification of the basic strokes in a hand-drawn geometrical graph is the main task in computer recognition. Usually, 2 or 3 basic strokes may be drawn at a time without any break in between. It is therefore necessary to consider separately the straight line, the arc and the combination of the two when a computer is used for the classification.An integrated discrimination approach with "angle-sum variable" and "maximum distance" is described. This method has been successfully used to classify basic drawing elements, the straight line, arc, circle, broken line and broken curve; Online recognition has been accomplished using an experimental system with flow chart symbols as an example. The recognizing rate is 94.0-99.5% for a single graphical symbol and there is no appreciable waiting time.
出处
《华中科技大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
1989年第S1期105-109,共5页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
关键词
手绘图形
机器识别
在线识别
流程图
线图
Man-made drawing
Computer recognition
On-line recognition
chart
Graphic