[1]李兰英,周志刚,陈德运. DBN和CNN融合的脱机手写汉字识别[J].哈尔滨理工大学学报,2020,25(03):137-143.[doi:1015938/jjhust202003021]
 LI Lan ying,ZHOU Zhi gang,CHEN De yun. Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model[J].哈尔滨理工大学学报,2020,25(03):137-143.[doi:1015938/jjhust202003021]
点击复制

 DBN和CNN融合的脱机手写汉字识别()
分享到:

《哈尔滨理工大学学报》[ISSN:1007-2683/CN:23-1404/N]

卷:
25
期数:
2020年03期
页码:
137-143
栏目:
计算机与控制工程
出版日期:
2020-06-25

文章信息/Info

Title:
 Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model
文章编号:
1007-2683(2020)03-0137-07
作者:
 李兰英周志刚陈德运
 
哈尔滨理工大学 计算机科学与技术学院,哈尔滨 150080)
Author(s):
 LI Lanying ZHOU Zhigang CHEN Deyun
 
(School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China)

关键词:
 关键词:卷积神经网络深度信念网络脱机手写汉字
Keywords:
 Keywords:convolutional neural network deep belief network offline handwritten chinese character
分类号:
TP3914
DOI:
1015938/jjhust202003021
文献标志码:
A
摘要:
 摘要:针对脱机手写汉字形近字多,提取特征难,识别不准的问题,提出了一种卷积神经网络和深度信念网络的融合模型。首先在数据集上分别训练卷积神经网络和深度信念网络,发现二者的综合TOP-2准确率可达到9933%。利用卷积神经网络和深度信念网络在图像分析中各自的优势,采用了一种融合比较策略,在两者的TOP-2分类中尽可能准确地取出一个分类结果以提高识别的能力。实验结果表明:卷积神经网络和深度信念网络的融合模型比单独使用卷积神经网络和深度信念网络具有更好的识别效果。
Abstract:
 Abstract:Aiming at the problem that some offline handwritten Chinese characters are similar in shape and it is difficult to extract the feature of characters and the recognition is not accurate, a convolutional neural network and deep belief network fusion model is proposed Firstly, the convolutional neural network and the deep belief network are trained on the dataset respectively It is found that the comprehensive TOP-2 accuracy of the both can reach 9933% Using the advantages of convolutional neural networks and deep belief networks in image analysis, a fusion comparison strategy is adopted to extract a classification result as accurately as possible in the TOP-2 classification of the two to improve the recognition ability The experimental results show that the fusion model of convolutional neural network and deep belief network has better recognition effect than convolutional neural network and deep belief network


参考文献/References:

[1]SHEN XI, RONALDO MESSIN. A Method of Synthesizing Handwritten Chinese Images for Data Augmentation[C]//International Conference on Frontiers in Handwriting Recognition, Shenzhen, China, 2016: 114.
[2]闫喜亮, 王黎明. 卷积深度神经网络的手写汉字识别系统[J]. 计算机工程与应用, 2017, 53(10): 246.
YAN Xiliang, WANG Liming. Handwritten Chinese Character Recognition System Based on Neural Network Convolution Depth[J]. Computer Engineering and Applications, 2017, 53(10):246.
〖LM〗[3]金连文, 钟卓耀, 杨 钊. 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.
JIN Lianwen, ZHONG Zhuoyao, YANG Zhao. Applications of Deep Learning for Handwritten Chinese Character Recognition: A Review[J]. ACTA AUTOMATICA SINICA, 2016, 42(8): 1125.
[4]WU Peilun, WANG Fayu, LIU Jianyang. An Integrated Multi-Classifier Method for Handwritten Chinese Medicine Prescription Recognition[C]//International Conference on Software Engineering and Service Science, Beijing, China, 2018: 1.
[5]WANG Zirui, DU Jun. Writer Code Based Adaptation of Deep Neural Network for Offline Handwritten Chinese Text Recognition[C]//International Conference on Frontiers in Handwriting Recognition, Shenzhen, China, 2016: 548.
[6]钟治权, 袁进, 唐晓颖. 基于卷积神经网络的左右眼识别[J]. 计算机研究与发展, 2018, 55(8):1667.
ZHONG Zhiquan, YUAN Jin, TANG Xiaoying. Left-vs-Right Eye Discrimination Based on Convolutional Neural Network[J]. Journal of Computer Research and Development, 2018, 55(8): 1667.
[7]吕启, 窦勇, 牛新, 等. 基于DBN模型的遥感图像分类[J]. 计算机研究与发展, 2014, 51(9): 1911.
LV Qi, DOU Yong, NIU Xin, et al. Remote Sensing Image Classification Based on DBN Model[J]. Journal of Computer Research and Development, 2014, 51(9): 1911.
[8]杨怡, 王江晴, 朱宗晓. 基于仿射传播聚类的自适应手写字符识别[J]. 计算机应用, 2015, 35(3): 807.
YANG Yi, WANG Jiangqing, ZHU Zongxiao. Adaptive Handwritten Character Recognition Based on Affinity Propagation Clustering[J]. Journal of Computer Applications, 2015, 35(3): 807.
[9]周庆曙, 陈劲杰, 纪鹏飞. 基于SVM的多特征手写体汉字识别技术[J]. 电子科技, 2016, 29(8): 136.
ZHOU Qingshu, CHEN Jinjie, JI Pengfei. The Technology of Multiple Features Handwritten Chinese Character Recognition Based on SVM[J]. Electronic Sci. & Tech, 2016, 29(8): 136.
[10]叶枫, 邓衍晨, 汪敏,等. 部分级联特征的离线手写体汉字识别方法[J]. 2017, 26(8): 134.
YE Feng, DENG Yanchen, WANG Min, et al. Offline Hand-Written Chinese Character Recognition Based on Partial Cascade Feature[J]. Computer Systems & Applications, 2017, 26(8): 134.
[11]WANG Yanwei, LI Xin, LIU Changsong. An MQDF-CNN Hybrid Model for Offline Handwritten Chinese Character Recognition[C]// The 14th International Conference on Frontiers in Handwriting Recognition, Heraklion, Greece, September, 2014:246.
[12]LIU Lu, SUN Weiwei, DING Bo. Offline Handwritten Chinese Character Recognition Based on DBN Fusion Model[C]// Proceedings of the IEEE International Conference on Information and Automation, Ningbo, China, August, 2016:1807.
[13]张帆, 张良, 刘星, 等. 基于深度残差网络的脱机手写汉字识别研究[J]. 计算机测量与控制, 2017, 25(12): 259.
ZHANG Fan, ZHANG Liang, LIU Xing, et al. Recognition of Offline Handwritten Chinese Character Based on Deep Residual Network[J]. Computer Measurement & Control, 2017, 25(12): 259.
[14]YANG Xiao, HE Dafang, ZHOU Zihan. Improving Offline Handwritten Chinese Character Recognition by Iterative Refinement[C]//The 14th IAPR International Conference on Document Analysis and Recognition, Kyoto, Japan, November, 2017: 5.
[15]WANG Zirui, DU Jun, HU Jinshui, et al. Deep Convolutional Neural Network Based Hidden Markov Model for Offline Handwritten Chinese Text Recognition[C]//Asian Conference on Pattern Recognition, Nanjing, China, November, 2017: 26.
[16]YANG Shimeng, NIAN Fudong, LI Teng. A light and Discriminative Deep Networks for Offline Handwritten Chinese Character Recognition[C]// The 32nd Youth Academic Annual Conference of Chinese Association of Automation, Hefei, China, May, 2017:785.
[17]ZHUANG Hang, LI Changlong, ZHOU Xuehai. CCRS: Web Service for Chinese Character Recognition[C]//IEEE International Conference on Web Services, San Francisco, CA, USA, July, 2018:17.
[18]YANN LECUN, LEON BOTTOU, YOSHUA BENGIO. Gradient-Based Learning Applied to Document Recognition[J]. IEEE Journals and Magazines, 1998, 86(11):1.
[19]LIU Chenglin, YIN Fei, WANG Dahan. CASIA Online and Offline Chinese Handeriting Databases[C]//International Conference on Document Analysis and Recognition, Beijing, China, November, 2011: 37.
[20]YIN Fei, WANG Qiufeng, ZHANG Xuyao. ICDAR 2013 Chinese Handwriting Recognition Competition[C]//The 12th International Conference on Document Analysis and Recognition, Washington, DC, USA, August, 2013:1464.


相似文献/References:

[1]孙永全,郭建英,陈洪科,等.AMSAA模型可靠性增长预测方法的改进[J].哈尔滨理工大学学报,2010,15(05):49.
 SUN Yong-quan,GUO Jian-ying,CHEN Hong-ke,et al.An Improved Reliability Growth Prediction Algorithm Based on AMSAA Model[J].哈尔滨理工大学学报,2010,15(03):49.
[2]滕志军,李晓霞,郑权龙,等.矿井巷道的MIMO信道几何模型及其信道容量分析[J].哈尔滨理工大学学报,2012,17(02):14.
 TENG Zhi-jun,LI Xiao-xia,ZHENG Quan-long.Geometric Model for Mine MIMO Channels and Its Capacity Analysis[J].哈尔滨理工大学学报,2012,17(03):14.
[3]李艳苹,张礼勇.新训练序列下的改进OFDM符号定时算法[J].哈尔滨理工大学学报,2012,17(02):19.
 LI Yan-ping,ZHANG Li-yong.An Improved Algorithm of OFDM Symbol Timing Based on A New Training Sequence[J].哈尔滨理工大学学报,2012,17(03):19.
[4]赵彦玲,车春雨,铉佳平,等.钢球全表面螺旋线展开机构运动特性分析[J].哈尔滨理工大学学报,2013,18(01):37.
 ZHAO Yan-ling,CHE Chun-yu,XUAN Jia-ping,et al.[J].哈尔滨理工大学学报,2013,18(03):37.
[5]李冬梅,卢旸,刘伟华,等.一类具有连续接种的自治SEIR传染病模型[J].哈尔滨理工大学学报,2013,18(01):73.
 LI Dong-mei,LU Yang,LIU Wei-hua.[J].哈尔滨理工大学学报,2013,18(03):73.
[6]华秀英,刘文德.奇Hamiltonian李超代数偶部的非负Z-齐次导子空间[J].哈尔滨理工大学学报,2013,18(01):76.
 HUA Xiu-ying,LIU Wen-de.[J].哈尔滨理工大学学报,2013,18(03):76.
[7]桂存兵,刘洋,何业军,等.基于LCC谐振电路阻抗匹配的光伏发电最大功率点跟踪[J].哈尔滨理工大学学报,2013,18(01):90.
 GUI Cun-bing,LIU Yong,HE Ye-jun.[J].哈尔滨理工大学学报,2013,18(03):90.
[8]翁凌,闫利文,夏乾善,等.PI/TiC@Al2O3复合薄膜的制备及其电性能研究[J].哈尔滨理工大学学报,2013,18(02):25.
 WENG Ling,YAN Li-wen,XIA Qian-shan.[J].哈尔滨理工大学学报,2013,18(03):25.
[9]姜彬,林爱琴,王松涛,等.高速铣刀安全性设计理论与方法[J].哈尔滨理工大学学报,2013,18(02):63.
 JIANG Bin,LIN Ai-qin,WANG Song-tao,et al.[J].哈尔滨理工大学学报,2013,18(03):63.
[10]李星纬,李晓东,张颖彧,等.EVOH 磺酸锂电池隔膜的制备及微观形貌[J].哈尔滨理工大学学报,2013,18(05):18.
 LI Xing- wei,LI Xiao- dong,ZHANG Ying- yu,et al.The Preparation and Microcosmic Morphology oEVOH- SO Li Lithium Ion Battery Septum[J].哈尔滨理工大学学报,2013,18(03):18.

备注/Memo

备注/Memo:

收稿日期: 2018-09-30
基金项目: 国家自然科学基金青年基金(61501147)
作者简介:
李兰英(1964—),女,硕士,教授,硕士研究生导师;
陈德运(1962—),男,博士,教授,博士研究生导师
通信作者:
周志刚(1991—),男,硕士研究生,Email:15127781106@163com
更新日期/Last Update: 2020-10-14