基于CNN图像识别与语义可靠性的路径搜索方法

doi:10.19678/j.issn.1000-3428.0056844

摘要/Abstract

摘要： 光学字符识别技术可有效提高票据应用中票据信息录入的工作效率。针对票据的复杂背景与不规范手写字符降低票据识别准确率的问题，结合卷积神经网络图像识别与语义可靠性，提出一种可靠性优先的路径搜索方法，以降低模糊字符对搜索路径的干扰。利用基于公司名结构特点的前后缀推断策略，有效解决公司名前后缀识别错误问题。采用结巴中文分词与字符位置信息检查识别结果中的错误，并将长短期记忆语言模型与在传统字形相似度基础上引入的汉字部件相似度相结合进行纠错。实验结果表明，通过将纠错策略与该方法相结合可有效提高公司名识别准确率至93.08%。

关键词: 文本识别, 语言模型, 卷积神经网络, 长短期记忆网络, 字形相似度, 结巴中文分词

Abstract: Optical Character Recognition(OCR) technology can effectively improve working efficiency of bills information input in bills application.To address the problem that the complex background of bills and irregular handwritten characters reduce the recognition accuracy of bills,this paper combines the Convolutional Neural Network(CNN) image recognition and semantic reliability to propose a reliability first path search method to reduce the interference of fuzzy characters on the search path.By using the prefix and suffix inference strategy proposed according to the structural characteristics of the company name,the problem of identifying the prefix and suffix of the company name is effectively solved.Jieba Chinese word segmentation and character position information are used to check the errors in the recognition results,and the Long Short-Term Memory(LSTM) language model is combined with the similarity of Chinese character components introduced based on the traditional character pattern similarity for error correction.The experimental results show that the proposed method combined with error correction strategies can significantly improve the accuracy of company name recognition,which reaches 93.08%.

Key words: text recognition, language model, Convolutional Neural Network(CNN), Long Short-Term Memory(LSTM) network, character pattern similarity, Jieba Chinese word segmentation

中图分类号:

TP391

李宇霞, 孙永奇, 闫茹, 朱卫国. 基于CNN图像识别与语义可靠性的路径搜索方法[J]. 计算机工程, 2021, 47(1): 255-263,274.

LI Yuxia, SUN Yongqi, YAN Ru, ZHU Weiguo. Path Search Method Based on CNN Image Recognition and Semantic Reliability[J]. Computer Engineering, 2021, 47(1): 255-263,274.

https://www.ecice06.com/CN/Y2021/V47/I1/255

图/表 13

20210125164835

20210125164839

20210125164842

20210125164846

20210125164849

20210125164853

20210125164857

20210125164900

20210125164903

20210125164906

20210125164909

20210125164912

20210125164916

参考文献

[1] HAN Mengdi,CAO Yudong,DU Gang.Recognition algorithms on bank bills image with BP network[J].Information & Communications,2016(9):157-159.(in Chinese)韩梦迪,曹玉东,杜刚.基于BP神经网络的银行票据识别[J].信息通信,2016(9):157-159.
[2] WANG Z R,DU J,WANG W C,et al.A comprehensive study of hybrid neural network hidden Markov model for offline handwritten Chinese text recognition[J].International Journal on Document Analysis and Recognition,2018,21(4):241-251.
[3] FU Qiang,DING Xiaoqing,LIU Tong,et al.A novel segmentation and recognition algorithm for Chinese handwritten address character strings[C]//Proceedings of ICPR'06.Washington D.C.,USA:IEEE Press,2006:974-977.
[4] LIU C L,KOGA M,FUJISAWA H.Lexicon-driven segmentation and recognition of handwritten character strings for Japanese address reading[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(11):1425-1437.
[5] WANG Qiufeng,YIN Fei,LIU Chenglin.Integrating language model in handwritten Chinese text recognition[C]//Proceedings of the 10th International Conference on Document Analysis and Recognition.Washington D.C.,USA:IEEE Press, 2009:1036-1040.
[6] WANG Qiufeng,YIN Fei,LIU Chenglin.Handwritten Chinese text recognition by integrating multiple contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(8):1469-1481.
[7] LIU Chenglin,YIN Fei,WANG Dahan,et al.CASIA online and offline Chinese handwriting databases[C]//Proceedings of 2011 International Conference on Document Analysis and Recognition.Washington D.C.,USA:IEEE Press,2011:37-41.
[8] WU Yichao,YIN Fei,LIU Chenglin.Evaluation of neural network language models in handwritten Chinese text recognition[C]//Proceedings of the 13th International Conference on Document Analysis and Recognition.Washington D.C.,USA:IEEE Press,2015:166-170.
[9] WANG Song,CHEN Li,XU Liang,et al.Deep knowledge training and heterogeneous CNN for handwritten Chinese text recognition[C]//Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition.Washington D.C.,USA:IEEE Press,2016:84-89.
[10] ZHOU X D,WANG D H,TIAN F,et al.Handwritten Chinese/Japanese text recognition using semi-Markov conditional random fields[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(10):2413-2426.
[11] WU Yichao,YIN Fei,LIU Chenglin.Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models[J].Pattern Recognition,2017,65:251-264.
[12] MESSINA R,LOURADOUR J.Segmentation-free handwritten Chinese text recognition with LSTM-RNN[C]//Proceedings of the 13th International Conference on Document Analysis and Recognition.Washington D.C.,USA:IEEE Press,2015:171-175.
[13] LI Hongzhu,WANG Weiqiang,LV Ke.N-FTRN:neighborhoods based fully convolutional network for Chinese text line recognition[J].Multimedia Tools and Applications,2019,78(16):22249-22268.
[14] WANG Zirui,DU Jun,HU Jinshui,et al.Deep convolutional neural network based hidden Markov model for offline handwritten Chinese text recognition[C]//Proceedings of the 4th IAPR Asian Conference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:816-821.
[15] WANG Wenchao,DU Jun,WANG Zirui.Parsimonious HMMs for offline handwritten Chinese text recognition[C]//Proceedings of the 16th International Conference on Frontiers in Handwriting Recognition.Washington D.C.,USA:IEEE Press,2018:145-150.
[16] YU Junjie,LI Zhenghua.Chinese spelling error detection and correction based on language model,pronunciation,and shape[EB/OL].[2019-11-08].https://www.aclweb.org/anthology/W14-6835.pdf.
[17] LIU C L,LAI M H,TIEN K W,et al.Visually and phonologically similar characters in incorrect Chinese words[J].ACM Transactions on Asian Language Information Processing,2011,10(2):1-39.
[18] LIU Hanwen.A Chinese word correction approach[EB/OL].[2019-11-08].https://github.com/liu-hanwen/ChineseCorrector/blob/master/Report.pdf.
[19] SUN Junyi."Jieba" Chinese word segmentation tool[EB/OL].[2019-11-08].https://github.com/fxsjy/jieba.
[20] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-11-08].https://arxiv.org/abs/1409.1556.
[21] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Delving deep into rectifiers:surpassing human-level performance on ImageNet classification[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:1026-1034.
[22] HIT-COMPUTER.Implement character-level language models for text generation based-on LSTM[EB/OL].[2019-11-08].https://github.com/hit-computer/char-rnn-tf.
[23] YU Jinxing,JIAN Xun,XIN Hao,et al.Joint embeddings of Chinese words,characters,and fine-grained subcharacter components[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing,Copenhagen,Denmark.Stroudsburg,USA:Association for Computational Linguistics,2017:286-291.
[24] YIN Fei,WANG Qiufeng,ZHANG Xuyao,et al.ICDAR 2013 Chinese handwriting recognition competition[EB/OL].[2019-11-08].http://www.nlpr.ia.ac.cn/2013papers/gjhy/gh66.pdf.
[25] XIAO Xuefeng,JIN Lianwen,YANG Yafeng,et al.Building fast and compact convolutional neural networks for offline handwritten Chinese character recognition[J].Pattern Recognition,2017,72:72-81.

选择文件类型/文献管理软件名称

选择包含的内容