摘要
本文首先介绍了文字识别的研究背景,然后介绍了基于深度学习的文字检测常用的网络模型,以及识别技术所用到的网络模型,总结了各网络的优点、缺点。之后介绍了信息提取时所用到的方法,比较了各种方法的优缺点,最后对全文进行了综合分析,并对文字识别与信息提取的未来发展做出了展望。
This paper first introduces the research background of text recognition,then introduces the network model of text detection based on deep learning,and the network model used in recognition technology,and summarizes the advantages and disadvantages of each network.Then it introduces the methods used in information extraction and compares the advantages and disadvantages of various methods.Finally,it makes a comprehensive analysis of the whole paper and makes a prospect for the future development of text recognition and information extraction.
作者
袁伟
郭欣
田红楠
YUAN Wei;GUO Xin;TIAN Hong-Nan(College of Artificial Intelligence And Data Science,Hebei University of Technology,Tianjin 300130,China;Qinhuangdao Research Institute,National Rehabilitation Auxiliary Research Center,Qinhuangdao Hebei066000,China)
出处
《机电产品开发与创新》
2020年第6期138-140,147,共4页
Development & Innovation of Machinery & Electrical Products
关键词
文字识别
深度学习
文字检测
信息提取
Text recognition
Deep learning
Text detection
Information extraction