基于CNN与有限状态自动机的手写体大写金额识别

doi:10.19678/j.issn.1000-3428.0059118

摘要/Abstract

摘要： 手写票据识别是模式识别中的研究难点之一，手写体风格多样、票据背景复杂等原因导致手写票据识别的准确率不高。大写金额作为票据中最重要的部分，对其进行准确识别是手写票据自动识别的关键。对基于分割的手写体大写金额识别及处理问题进行研究，提出一种基于卷积神经网络（CNN）与有限状态自动机的手写体大写金额识别方法。在利用过分割和组合过分割项得到单字符后使用CNN对其进行识别。通过对字符进行分类、定义各类字符之间的逻辑关系构造用于语法检查的有限状态自动机，通过语法自动机在识别结果中选择符合语法规则的字符串，并在路径搜索中利用语法自动机优化搜索性能。在此基础上，运用语法自动机对模糊字符进行预测，以纠正CNN的识别错误。实验结果表明，该方法在对大写金额单字符和文本行进行识别时准确率分别高达98.2%与96.6%。

关键词: 卷积神经网络, 有限状态自动机, 手写票据识别, 大写金额, 光学字符识别, 模式识别

Abstract: The handwritten check recognition is a tough problem in pattern recognition.The challenge is that various handwriting styles and complex check backgrounds reduce the recognition accuracy.The capitalized Chinese currency amount is the most important part of a check, and its recognition is key to automatic processing of handwritten check images.This paper presents the study of segmentation-based recognition of handwritten capitalized Chinese currency amounts, and on this basis proposes a recognition method based on Convolutional Neural Network(CNN) and finite state automata.The method employs the over-segmented items and their combinations to obtain single characters, which are subsequently recognized by using CNN.Then the characters are categorized, and the logic relationships between them are defined to construct a finite state automaton for grammar detection.The automaton is used to select the grammatically correct strings from the recognition results, and the grammar automaton is used to optimize the performance of paths search.In addition, the grammar automaton is used to predict the fuzzy characters to correct the errors in the recognition results of CNN.The experimental results show that the accuracy of the proposed method achieves 98.2% for capitalized single characters, and 96.6% for text lines of currency amounts.

Key words: Convolutional Neural Network(CNN), finite state automata, handwritten bank check recognition, capitalized Chinese currency amounts, optical character recognition, pattern recognition

中图分类号:

TP391

闫茹, 孙永奇, 朱卫国, 李宇霞. 基于CNN与有限状态自动机的手写体大写金额识别[J]. 计算机工程, 2021, 47(9): 304-312.

YAN Ru, SUN Yongqi, ZHU Weiguo, LI Yuxia. Recognition of Handwritten Capitalized Chinese Currency Amounts Based on CNN and Finite State Automata[J]. Computer Engineering, 2021, 47(9): 304-312.

https://www.ecice06.com/CN/Y2021/V47/I9/304

图/表 8

20210917193123

20210917193131

20210917193135

20210917193138

20210917193142

20210917193146

20210917193149

20210917193153

参考文献

[1] HUANG L L, LI S T, LI L M.Extraction of filled-in items from Chinese bank check using support vector machines[C]//Proceedings of the 4th International Symposium on Neural Networks:Advances in Neural Networks.Berlin, Germany:Springer, 2007:407-415.
[2] WANG S, MA F, XIA S W.A Chinese bank check recognition system based on the fault tolerant technique[C]//Proceedings of the 4th International Conference on Document Analysis and Recognition.Berlin, Germany:Springer, 1997:1038-1042.
[3] DONG L, CHEN Y.A prototype system of courtesy amount recognition for Chinese bank checks[C]//Proceedings of IAPR International Workshop on Document Analysis Systems.Washington D.C., USA:IEEE Press, 2012:53-57.
[4] TANG H S, AUGUSTIN E, SUEN C Y, et al.Recognition of unconstrained legal amounts handwritten on Chinese bank checks[C]//Proceedings of the 17th International Conference on Pattern Recognition.Washington D.C., USA:IEEE Press, 2004:610-613.
[5] LOU Z, YANG J Y, JIN Z.Recognition and checkout of legal amounts on Chinese bank cheques[C]//Proceedings of International Conference on Wavelet Analysis & Pattern Recognition.Washington D.C., USA:IEEE Press, 2008:35-39.
[6] CHI B Y, CHEN Y B.Chinese handwritten legal amount recognition with HMM-based approach[C]//Proceedings of International Conference on Document Analysis and Recognition.Washington D.C., USA:IEEE Press, 2013:778-782.
[7] LIU X, HU B T, CHEN Q C, et al.Stroke sequence-dependent deep convolutional neural network for online handwritten Chinese character recognition[EB/OL].[2020-06-05].https://arxiv.org/pdf/1610.04057.pdf.
[8] GAN J, WANG W Q, LU K.Characters as graphs:recognizing online handwritten Chinese characters via spatial graph convolutional network[EB/OL].[2020-06-05].https://arxiv.org/pdf/2004.09412.pdf.
[9] MENG W, CHEN Y, WANG X.Recognition of handwritten characters in Chinese legal amounts by stacked autoencoders[C]//Proceedings of International Conference on Pattern Recognition.Washington D.C., USA:IEEE Press, 2014:12-36.
[10] YU M L, KWOK P C K, LEUNG C H, et al.Segmentation and recognition of Chinese bank check amounts[J].International Journal on Document Analysis and Recognition, 2001, 3(4):207-217.
[11] ZHANG X Y, BENGIO Y, LIU C L.Online and offline handwritten Chinese character recognition:a comprehensive study and new benchmark[EB/OL].[2020-06-05].https://arxiv.org/pdf/1606.05763.pdf.
[12] WANG Q F, YIN F, LIU C L.Integrating language model in handwritten Chinese text recognition[EB/OL].[2020-06-05].http://www.cvc.uab.es/icdar2009/papers/3725b036.pdf.
[13] WU Y C, YIN F, LIU C L.Evaluation of neural network language models in handwritten Chinese text recognition[EB/OL].[2020-06-05].https://ieeexplore.ieee.org/document/7333745.
[14] SHI B, XIANG B, CONG Y.An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 39(11):2298-2304.
[15] MESSINA R, LOURADOUR J.Segmentation-free handwritten Chinese text recognition with LSTM-RNN[C]//Proceedings of International Conference on Document Analysis and Recognition.Washington D.C., USA:IEEE Press, 2015:171-175.
[16] CHOMSKY N.Three models for the description of language[J].IRE Transactions on Information Theory, 1956, 2(3):113-124.
[17] 夏吾吉, 华却才让.基于有限状态自动机阿拉伯数字与藏文数词自动翻译[J].计算机工程与科学, 2018, 40(3):550-554. XIA W J, HUAQUE C R.Automatic translation between Arabic numerals and Tibetan numerals based on finite state automata[J].Computer Engineering and Science, 2018, 40(3):550-554.(in Chinese)
[18] GREGHI J G, MARTINS E.Semi-automatic generation of extended finite state machines from natural language standard documents[C]//Proceedings of IEEE International Conference on Dependable Systems and Networks Workshops.Washington D.C., USA:IEEE Press, 2015:45-50.
[19] RACHMAN F H, QUDSIYAH, SOLIHIN F.Finite state automata approach for text to speech translation system in Indonesian-Madurese language[J].Journal of Physics:Conference Series, 2020, 1569(2):022091.
[20] 孙玉强, 李玉萍, 王海燕, 等.确定有限自动机最小化算法的并行处理[J].计算机科学, 2008, 35(1):298-300. SUN Y Q, LI Y P, WANG H Y, et al.Parallel processing of minimization algorithm for determination finite automata[J].Computer Science, 2008, 35(1):298-300.(in Chinese)
[21] TIAN Z, HUANG W L, HE T, et al.Detecting text in natural image with connectionist text proposal network[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:56-75.
[22] 韩宇韬.数字正射影像镶嵌中色彩一致性处理的若干问题研究[D].武汉:武汉大学, 2014. HAN Y T.Research on key technology of color consistency processing for digital ortho map mosaicing[D].Wuhan:Wuhan University, 2014.(in Chinese)
[23] LIU C L, YIN F, WANG D H, et al.CASIA online and offline Chinese handwriting databases[C]//Proceedings of International Conference on Document Analysis and Recognition.Washington D.C., USA:IEEE Press, 2011:37-41.
[24] 中华人民共和国财政部令第98号.会计基础工作规范[EB/OL].[2020-06-05].http://tfs.mof.gov.cn/zhengwuxinxi/caizhengbuling/201903/t20190315_3193919.html. Order No.98 of the ministry of finance of the people's republic of China.Accounting basic work specification[EB/OL].[2020-06-05].http://tfs.mof.gov.cn/zhengwuxinxi/caizhengbuling/201903/t20190315_3193919.html.(in Chinese)
[25] WANG Q F, YIN F, LIU C L.Handwritten Chinese text recognition by integrating multiple contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 34(8):1469-1481.

选择文件类型/文献管理软件名称

选择包含的内容