深度学习在手写汉字识别中的应用综述  

Applications of Deep Learning for Handwritten Chinese Character Recognition:A Review

作　　者：金连文[1] 钟卓耀 杨钊[2] 杨维信 谢泽澄 孙俊 

机构地区：[1]华南理工大学电子与信息学院,广州510641 [2]广州大学机械与电气工程学院,广州510641 [3]富士通研究开发中心有限公司信息技术研究部,北京100190

出　　处：《自动化学报》2016年第8期1125-1141,共17页Acta Automatica Sinica

基　　金：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.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.

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 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]