摘要
以工商年检报表的自动录入处理为例,介绍了专用报表的扫描与识别技术.分析了专用报表的格式设计、扫描图形的校正与噪声的过滤、特征点与特征曲线的提取.采用基于结构特征的模糊初分法和相容松弛匹配法由计算机对专用报表上填写的各种数据与特殊符号进行自动识别.
This paper introduces the technique of scanning and recognition of special purpose report form, taking the automatic data logging and processing of the industrial and commercial annual checking report forms for example. The format design of the report form, adjustment of scanned graph and filtering of noise, abstraction of characteristic points and curves are analysed. Then the fuzzy primary classification method based on structural characters along with the consistent relaxation matching method is adopted to recognize various numeral data and special symbols in the special purpose report form automatically by computer.
出处
《华南理工大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
1998年第9期90-96,共7页
Journal of South China University of Technology(Natural Science Edition)
关键词
专用报表
扫描
相容松驰匹配
自动识别
计算机
special purpose report form
scanning
recognition
fuzzy primary classification
consistent relaxation matching