Chinese document layout analysis based on adaptive split-and-merge and qualitative spatial reasoning

被引:10
|
作者
Liu, JM [1 ]
Tang, YY [1 ]
Suen, CY [1 ]
机构
[1] CONCORDIA UNIV,CTR PATTERN RECOGNIT & MACHINE INTELLIGENCE,MONTREAL,PQ H3G 1M8,CANADA
关键词
Chinese document processing; geometric structure; adaptive split-and-merge; segment spatial reasoning;
D O I
10.1016/S0031-3203(96)00165-3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The ultimate goal of automatic document processing is to understand the semantics of a document. Towards such an end, one of the primary enabling steps has been to first reason about the layout of the document by means of page segmentation and segment spatial reasoning or labeling. This, in turn, allows for the derivation of document logical organization. This paper describes a generic document segmentation and geometric relation labeling method with applications to Chinese document analysis. Unlike the previous document segmentation methods where text spacing, border lines, and/or a priori layout models based on template matching processing are performed, the present method begins with a hierarchy of partitioned image layers where inhomogeneous higher-level regions are recursively partitioned into lower-level rectangular subregions and at the same time lower-level smaller homogeneous regions are merged into larger homogeneous regions. Furthermore, the derived segment data structure readily enables efficient search for geometric relationships between identified document segments. (C) 1997 pattern Recognition Society. Published by Elsevier Science Ltd.
引用
收藏
页码:1265 / 1278
页数:14
相关论文
共 50 条
  • [1] Density Peak Clustering Based Split-and-Merge
    Lu, Jixiang
    Zhong, Caiming
    [J]. ROUGH SETS, IJCRS 2022, 2022, 13633 : 191 - 202
  • [2] ADAPTIVE SPLIT-AND-MERGE SEGMENTATION BASED ON PIECEWISE LEAST-SQUARE APPROXIMATION
    WU, XL
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (08) : 808 - 815
  • [3] Adaptive Split-and-Merge Clustering Algorithm for Wireless Sensor Networks
    Zhang, Yong
    Li, Keqiu
    Gu, Hong
    Yang, Dongwei
    [J]. 2012 INTERNATIONAL WORKSHOP ON INFORMATION AND ELECTRONICS ENGINEERING, 2012, 29 : 3547 - 3551
  • [4] Evidential split-and-merge: Application to object-based image analysis
    Lachaize, Marie
    Le Hegarat-Mascle, Sylvie
    Aldea, Emanuel
    Maitrot, Aude
    Reynaud, Roger
    [J]. INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2018, 103 : 303 - 319
  • [5] A projection-based split-and-merge clustering algorithm
    Cheng, Mingchang
    Ma, Tiefeng
    Liu, Youbo
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2019, 116 : 121 - 130
  • [6] Edge-based split-and-merge superpixel segmentation
    School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China
    [J]. IEEE Int. Conf. Inf. Autom., ICIA - conjunction IEEE Int. Conf. Autom. Logist., 2015, (970-975):
  • [7] Edge-Based Split-and-Merge Superpixel Segmentation
    Li, Li
    Yao, Jian
    Tu, Jinge
    Lu, Xiaohu
    Li, Kai
    Liu, Yahui
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION, 2015, : 970 - 975
  • [8] A Parallel Framework for Processing Massive Spatial Data with a Split-and-Merge Paradigm
    Guan, Xuefeng
    Wu, Huayi
    Li, Lin
    [J]. TRANSACTIONS IN GIS, 2012, 16 (06) : 829 - 843
  • [9] An adaptive split-and-merge method for binary image contour data compression
    Xiao, Y
    Zou, JJ
    Yan, H
    [J]. PATTERN RECOGNITION LETTERS, 2001, 22 (3-4) : 299 - 307
  • [10] SPLIT-AND-MERGE IMAGE SEGMENTATION BASED ON LOCALIZED FEATURE ANALYSIS AND STATISTICAL TESTS
    CHEN, SY
    LIN, WC
    CHEN, CT
    [J]. CVGIP-GRAPHICAL MODELS AND IMAGE PROCESSING, 1991, 53 (05): : 457 - 475