[1]武子毅,刘亮亮,张再跃.基于集成注意力层卷积神经网络的汉字识别[J].计算机技术与发展,2018,28(08):100-103.[doi:10.3969/ j. issn.1673-629X.2018.08.021]
　WU Zi-yi,LIU Liang-liang,ZHANG Zai-yue.Chinese Character Recognition of Convolutional Neural Network of Integration Attention Layer[J].,2018,28(08):100-103.[doi:10.3969/ j. issn.1673-629X.2018.08.021]
点击复制

基于集成注意力层卷积神经网络的汉字识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年08期
页码:
100-103
栏目:
智能、算法、系统工程
出版日期:
2018-08-10

文章信息/Info

Title:
Chinese Character Recognition of Convolutional Neural Network of Integration Attention Layer
文章编号:
1673-629X(2018)08-0100-04
作者:
武子毅 1 ; 刘亮亮 2 ; 张再跃 1
1. 江苏科技大学 计算机学院,江苏 镇江 212003; 2. 上海对外经贸大学 统计与信息学院,上海 201620
Author(s):
WU Zi-yi 1 ; LIU Liang-liang 2 ; ZHANG Zai-yue 1
1.School of Computer Science and Engineering,Jiangsu University of Science and Technology,Zhenjiang 212003,China; 2.Schoolof Statistics and Information,Shanghai University of International Business and Economics,Shanghai 201620,China
关键词:
卷积神经网络; AlexNet; 注意力层; 汉字识别
Keywords:
convolutional neural network; AlexNet; attention layer; Chinese character recognition
分类号:
TP301
DOI:
10.3969/ j. issn.1673-629X.2018.08.021
文献标志码:
A
摘要:
针对传统汉字识别受特征提取方法的限制,选择卷积神经网络作为汉字识别的模型。 介绍了选择卷积神经网络基准模型的过程,选择 AlexNet 网络模型作为基准模型,并且详细介绍了 AlexNet 的网络配置。 为了解决形相似汉字的微小差异会在训练中丢失的问题,通过将注意力层与选定的 AlexNet 网络中的卷积层进行并联,以提高汉字图像中微小差异处的权重,达到提高该处注意力的目的,从而减少卷积层对于丢失信息的影响,提高识别效果。 实验结果表明,相比传统汉字识别方法,多层卷积神经网络模型自动提取特征的方法在汉字识别中的效果有显著提高。 相比普通卷积神经网络, 改进方法在准确率和召回率上均有一定提高。
Abstract:
In order to solve the problem that the traditional Chinese character recognition is limited by the feature extraction method,the convolutional neural network is chosen as the model of Chinese character recognition. We introduce the process of selecting the bench- mark model of convolutional neural network and choose the AlexNet as the benchmark model,the network configuration of which is in- troduced in detail. In order to solve the problem that the minor differences among the Chinese characters of similar shape will be lost in the training process,the weight of small differences at the Chinese characters image are increased through the convolution layer of the se- lected AlexNet and the attention layer in parallel. The results show that the added attention layer can reduce the impact of the deep layers for losing information,thereby improving performance. The experiment shows that compared with the traditional Chinese character recog- nition method,the automatic feature extraction method of multilayer convolution neural network model has a significant improvement in Chinese character recognition. And compared with ordinary convolution neural network,the improved method has certain improvement in accuracy and recall rate.

相似文献/References:

[1]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].,2018,28(08):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[2]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(08):31.
[3]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(08):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[4]郭子琰,舒心,刘常燕,等.基于ReLU 函数的卷积神经网络的花卉识别算法[J].计算机技术与发展,2018,28(05):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
　GUO Ziyan,SHU Xin,LIU Changyan,et al.A Recognition Algorithm of Flower Based on Convolution Neural Network with ReLU Function[J].,2018,28(08):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
[5]缪宇杰,吴智钧,宫 婧.基于3D 卷积的视频错帧筛选方法[J].计算机技术与发展,2018,28(05):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
　MIAO Yu-jie,WU Zhi-jun,GONG Jing.A Wrong Temporal-order Frames Identification Method Based on 3D Convolution[J].,2018,28(08):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
[6]吴玉枝,吴志红,熊运余.基于卷积神经网络的小样本车辆检测与识别[J].计算机技术与发展,2018,28(06):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
　WU Yu-zhi,WU Zhi-hong,XIONG Yun-yu.Vehicle Detection and Recognition of a Few Samples Based on Convolutional Neural Network[J].,2018,28(08):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
[7]李相桥,李晨,田丽华,等.卷积神经网络并行训练的优化研究[J].计算机技术与发展,2018,28(08):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
　LI Xiang-qiao,LI Chen,TIAN Li-hua,et al.Research on Optimization of Parallel Training for Convolution Neural Network[J].,2018,28(08):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
[8]邓宗平,赵启军,陈虎. 基于深度学习的人脸姿态分类方法[J].计算机技术与发展,2016,26(07):11.
　DEND Zong-ping,ZHAO Qi-jun,CHEN Hu. Face Pose Classification Method Based on Deep Learning[J].,2016,26(08):11.
[9]河海大学 计算机与信息学院,江苏 南京 0098.卷积网络的无监督特征提取对人脸识别的研究[J].计算机技术与发展,2018,28(06):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
　DU Bai-sheng.Research on Unsupervised Feature Extraction Based on Convolutional Neural Network for Face Recognition[J].,2018,28(08):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
[10]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(08):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[11]袁小平,石 慧.基于迁移学习的鱼类识别方法研究[J].计算机技术与发展,2021,31(04):52.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 009]
　YUAN Xiao-ping,SHI Hui.Research on Fish Recognition Method Based on Transfer Learning[J].,2021,31(08):52.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 009]
[12]林　峰,向　忠.基于深度学习的印花织物循环图案基元分割[J].计算机技术与发展,2022,32(05):160.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 027]
　LIN Feng,XIANG Zhong.Primitive Segmentation of Repeat Patterns on Printed Fabrics Based on Deep Learning[J].,2022,32(08):160.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 027]

更新日期/Last Update: 2018-09-10