基于深度学习的场景文字检测综述  

Deep Learning Based Scene Text Detection:A Survey

作　　者：姜维 张重生[2] 殷绪成[3] JIANG Wei;ZHANG Chong-sheng;YIN Xu-cheng(School of Information Engineering,North China University of Water Resources and Electric Power,Zhengzhou,Henan 450045,China;School of Computer and Information Engineering,Henan University,Kaifeng,Henan 475001,China;School of Computer and Communication Engineering,University of Science and Technology Beijing,Beijing 100083,China)

机构地区：[1]华北水利水电大学信息工程学院,河南郑州450045 [2]河南大学计算机与信息工程学院,河南开封475001 [3]北京科技大学计算机与通信工程学院,北京100083

出　　处：《电子学报》2019年第5期1152-1161,共10页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61601184;No.61562058);河南省高等学校重点科研项目(No.16A520018)

摘　　要：近年来,基于深度学习的场景文字检测技术取得重要进展.本文综述了该技术在2014～2018年间的最新工作,将其分为传统区域建议方法、文字建议网络方法、基于分割的方法以及文字建议网络与分割的混合方法,并对各类方法的优劣进行分析.本文还展望了未来发展趋势,指出未来研究热点.In recent years,deep learning based scene text detection have achieved significant progress.The paper reviews state-of-the-art methods in the field from 2014-2018.We categorize existing methods into traditional Region Proposal based method,Text Proposal Network method,segmentation based method and hybrid method based on Text Proposal Network and segmentation with detailed analysis of pros and cons for the four methods.Finally,we point out research trends and focuses in this field.

关 键 词：深度学习 场景文字 检测定位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]