首页 | 本学科首页   官方微博 | 高级检索  
     

深度学习在手写汉字识别中的应用综述
引用本文:金连文,钟卓耀,杨钊,杨维信,谢泽澄,孙俊.深度学习在手写汉字识别中的应用综述[J].自动化学报,2016,42(8):1125-1141.
作者姓名:金连文  钟卓耀  杨钊  杨维信  谢泽澄  孙俊
作者单位:1.华南理工大学电子与信息学院 广州 510641
基金项目:国家自然科学基金(61472144),广东省科技计划(2014A010103012,2015B010101004,2015B010130003,2015B010131004)资助
摘    要:手写汉字识别(Handwritten Chinese character recognition,HCCR)是模式识别的一个重要研究领域,最近几十年来得到了广泛的研究与关注,随着深度学习新技术的出现,近年来基于深度学习的手写汉字识别在方法和性能上得到了突破性的进展.本文综述了深度学习在手写汉字识别领域的研究进展及具体应用.首先介绍了手写汉字识别的研究背景与现状.其次简要概述了深度学习的几种典型结构模型并介绍了一些主流的开源工具,在此基础上详细综述了基于深度学习的联机和脱机手写汉字识别的方法,阐述了相关方法的原理、技术细节、性能指标等现状情况,最后进行了分析与总结,指出了手写汉字识别领域仍需要解决的问题及未来的研究方向.

关 键 词:深度学习    手写汉字识别    卷积神经网络    回归神经网络    长短时记忆模型    层叠自动编码机
收稿时间:2015-11-04

Applications of Deep Learning for Handwritten Chinese Character Recognition: A Review
JIN Lian-Wen,ZHONG Zhuo-Yao,YANG Zhao,YANG Wei-Xin,XIE Ze-Cheng,SUN Jun.Applications of Deep Learning for Handwritten Chinese Character Recognition: A Review[J].Acta Automatica Sinica,2016,42(8):1125-1141.
Authors:JIN Lian-Wen  ZHONG Zhuo-Yao  YANG Zhao  YANG Wei-Xin  XIE Ze-Cheng  SUN Jun
Affiliation:1.School of Electronic and Information Engineering, South China University of Technology, Guangzhou 5106412.School of Mechanical and Electric Engineering, Guangzhou University, Guangzhou 5106413.Information Technology Laboratory, Fujitsu Research & Development Center Co., Ltd, Beijing 100190
Abstract:Handwritten Chinese character recognition (HCCR) is an important research filed of pattern recognition, which has attracted extensive studies during the past decades. With the emergence of deep learning, new breakthrough progresses of HCCR have been obtained in recent years. In this paper, we review the applications of deep learning models in the field of HCCR. First, the research background and current state-of-the-art HCCR technologies are introduced. Then, we provide a brief overview of several typical deep learning models, and introduce some widely used open source tools for deep learning. The approaches of online HCCR and offline HCCR based on deep learning are surveyed, with the summaries of the related methods, technical details, and performance analysis. Finally, further research directions are discussed.
Keywords:Deep learning  handwritten Chinese character recognition (HCCR)  convolutional neural network  recurrent neural network  long-short term memory (LSTM)  stacked auto-encoder
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号