面向电力作业的工作票分割与作业信息提取方法
CSTR:
作者:
通讯作者:

丘浩(1990—),男,硕士,工程师,主要从事电力系统运行与分析研究;E-mail:hq-ferd5689@qq.com

中图分类号:

TM721

基金项目:

广西电网有限责任公司科技项目(GXKJXM20190276)


Power operation oriented approach of work ticket segmentation and work information extraction method
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [18]
  • | | | |
  • 文章评论
    摘要:

    电力工作票中包含的电力作业关键信息是进行作业前风险评估的重要基础,为了快速且准确地从实际工作票文档中提取所需信息,提出一种电力工作票分割与作业信息提取方法。首先,采取二值化、膨胀和腐蚀等操作从电力工作票图像中提取表格框线;然后,基于框线检测结果对工作票进行分割操作得到单元格图片,再使用光学字符识别方法(OCR)检测各单元格内对应的作业信息;最后,基于正则匹配方法对识别结果进行结构化处理,实现电力作业信息的有效提取与匹配。基于实际多任务工作票的实验测试表明,所提方法能将提取到的电力作业信息按所属单元格进行合乎上下文语义的组合,关键信息识别效果优于通用商业OCR软件。

    Abstract:

    The key information of system operation contained in the power work ticket is an important basis for pre-operation risk assessment. In order to quickly and accurately extract the required information from the actual work ticket document, a method of power work ticket segmentation and information extraction is proposed. First, the binarization, expansion, and corrosion operations are utilized to extract the table frame lines from the power work ticket image. Then the segmentation operations are performed to obtain cell images of the work ticket based on the frame lines detection results. The optical character recognition (OCR) is further leveraged to detect the corresponding information in the cell. Finally, the recognition result is structured based on the regular matching method to realize the effective extraction and matching of power operation information. Experimental tests based on actual work tickets show that the proposed method can combine the extracted power operation information in a contextual and semantic combination, and the key information recognition effect is better than general commercial OCR software.

    参考文献
    [1] 惠军.浅谈电力安全生产中的“两票”管理制度[J].湖北水力发电,2007(1):54-56.HU Jun."Two-Card"management system in electrical production[J].Hubei Water Power,2007(1):54-56.
    [2] 孙小龙,郝玉凤,樊宏亮,等.新能源场站“两票”管理及移动运维平台应用[J].电力安全技术,2020,22(4):49-53.SUN Xiaolong,HAO Yufeng,FAN Hongliang,et al."Two Tickets" management of new energy station and application of mobile operation and maintenance platform[J].Electric Safety Technology,2020,22(4):49-53.
    [3] LECUN Y,CORTES C,BURGES C J C.The MNIST database of handwritten digits[EB/OL].http://yann.lecun.com/exdb/mnist,1998.
    [4] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
    [5] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//3rd International Conference on Learning Representations(ICLR),San Diego,CA,US,2015.
    [6] SHI B G,BAI X,YAO C.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 and Machine Intelligence,2017,39(11):2298-2304.
    [7] 史建伟.基于深度学习的车牌识别系统的设计与实现[D].南京:南京邮电大学,2020.
    [8] 张振宇,姜贺云,樊明宇.一种面向银行票据文字自动化识别的高效人工智能方法[J].温州大学学报(自然科学版),2020,41(3):47-56.ZHANG Zhenyu,JIANG Heyun,FAN Mingyu,An efficient artificial intelligence method for automatic recognition of bank bill text[J].Journal of Wenzhou University(Natural Science Edition),2020,41(3):47-56.
    [9] SCHREIBER S,AGNE S,WOLF I,et al.DeepDeSRT:deep learning for detection and structure recognition of tables in document images[C]//14th IAPR International Conference on Document Analysis and Recognition(ICDAR),Kyoto,Japan,2017.
    [10] 陈科峻.票据字符识别平台研究与实现[D].长春:中国科学院大学(中国科学院长春光学精密机械与物理研究所),2020.
    [11] 徐楠楠,王东风,韩璞.基于正向最大匹配算法的电力两票安全识别[J].计算机仿真,2014,31(1):145-148+355.XU Nannan,WANG Dongfeng,HAN Pu.Recognition of two-tickets system in power station based on forward maximum matching algorithm[J].Computer Simulation,2014,31(1):145-148+355.
    [12] 李新良.基于模板匹配法的字符识别算法研究[J].计算技术与自动化,2012,31(2):90-93.LI Xinliang.Research on character recognition algorithm based on template matching method[J].Computing Technology and Automation,2012,31(2):90-93.
    [13] 刘莉.光学字符识别系统中关键算法的设计与研究[D].成都:电子科技大学,2011.
    [14] 周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报,2017,40(6):1229-1251.ZHOU Feiyan,JIN Linpeng,DONG Jun.Review of convolutional neural network[J].Chinese Journal of Computers,2017,40(6):1229-1251.
    [15] BOUREAU Y L,PONCE J,LECUN Y.A theoretical analysis of feature pooling in visual recognition[C]//27th international conference on machine learning(ICML),Haifa,Israel,2010.
    [16] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
    [17] 周余涵,张哲,韩杰祥,等.基于开—闭滤波和多分辨形态梯度的直流线路纵联保护新原理[J].中国电机工程学报,2020,40(6):1897-1906.ZHOU Yuhan,ZHANG Zhe,HAN Jiexiang,et al.A novel pilot protection based on open-close filtering and multi-resolution morphological gradient operators for HVDC transmission line[J].Proceedings of the CSEE,2020,40(6):1897-1906.
    [18] 奚雪峰,周国栋.面向自然语言处理的深度学习研究[J].自动化学报,2016,42(10):1445-1465.XI Xuefeng,ZHOU Guodong.A survey on deep learning for natural language processing[J].Acta Automatica Sinica,2016,42(10):1445-1465.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

丘浩,张炜,林翔宇,等.面向电力作业的工作票分割与作业信息提取方法[J].电力科学与技术学报,2022,37(6):198-205.
QIU Hao, ZHANG Wei, LIN Xiangyu, et al. Power operation oriented approach of work ticket segmentation and work information extraction method[J]. Journal of Electric Power Science and Technology,2022,37(6):198-205.

复制
分享
文章指标
  • 点击次数:376
  • 下载次数: 1042
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2023-01-16
文章二维码