Intelligent Frame and Table Segmentation in Blueprint Documents: Method and Implementation

被引:0
作者
Hasan, Fudail [1 ]
Kashevnik, Alexey [2 ,3 ]
机构
[1] ITMO Univ, St Petersburg, Russia
[2] SPC RAS, St Petersburg, Russia
[3] Petrozavodsk State Univ PetrSU, Petrozavodsk, Russia
来源
DATA SCIENCE AND ALGORITHMS IN SYSTEMS, 2022, VOL 2 | 2023年 / 597卷
关键词
Frame and table segmentation; Blueprint processing; Table detection; Lines segmentation;
D O I
10.1007/978-3-031-21438-7_71
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Blueprints are documents that contain the drawing of a design and the information that explains this design. Recently, the task to automatically recognize the information in the blueprint documents has become required. Segmenting the frame and tables in the blueprint is the first step of understanding the blueprint document. In this paper, we explain an automated method for frame and table segmentation. The proposed method processes the blueprint as an image and defines all the parts (pixels) of the blueprint that belongs to the frame or tables. It finds all the lines in the blueprint's image and decide which combinations of lines construct frame and tables. It can process blueprints that have high resolution. The proposed method allows to isolate frame and tables in the blueprint document. We achieved an accuracy of 99% for excellent quality documents.
引用
收藏
页码:837 / 845
页数:9
相关论文
共 6 条
  • [1] Cesarini F, 2002, INT C PATT RECOG, P236, DOI 10.1109/ICPR.2002.1047838
  • [2] On methods and tools of table detection, extraction and annotation in PDF documents
    Khusro, Shah
    Latif, Asima
    Ullah, Irfan
    [J]. JOURNAL OF INFORMATION SCIENCE, 2015, 41 (01) : 41 - 57
  • [3] DeepDeSRT: Deep Learning for Detection and Structure Recognition of Tables in Document Images
    Schreiber, Sebastian
    Agne, Stefan
    Wolf, Ivo
    Dengel, Andreas
    Ahmed, Sheraz
    [J]. 2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 1162 - 1167
  • [4] Siddiqui Shoaib Ahmed, 2019, 2019 International Conference on Document Analysis and Recognition (ICDAR). Proceedings, P1397, DOI 10.1109/ICDAR.2019.00225
  • [5] Tran Dieu Ni, 2015, International Journal of Contents, V11, P77
  • [6] Zuyev K, 1997, PROC INT CONF DOC, P705, DOI 10.1109/ICDAR.1997.620599