Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/32992
Title: Automatic recognition of tables in construction tender documents
Authors: Cao, Y
Wang, S
Li, H 
Keywords: Attributed relationship graph
Construction tender document
Form recognition
Table model
Issue Date: 2002
Publisher: Elsevier
Source: Automation in construction, 2002, v. 11, no. 5, p. 573-584 How to cite?
Journal: Automation in construction 
Abstract: The construction industry can gain much benefit from automation, especially in automatic document generation and recognition. In this paper, an automatic system for recognizing tables in construction tender documents is introduced. Tender documents contain a special kind of forms. The object-oriented attributed relationship graph (OO-ARG) is introduced to be the representation scheme for structuring the information contained in forms. The OO-ARG representation scheme is the core of the computer system for recognizing and interpreting tender documents. The system consists of two main modules: table modeler and table reader. The table modeler assists users to construct form models, and the table reader recognizes the input tables from the model database and re-generates electronic tables. Experimental results indicate that the system is efficient and applicable in recognizing construction tender documents.
Description: This special issue publishes a set of selected and revised papers originally presented at the International Conference for Construction IT 2000 (INCITE 2000) held on January 17–18, 2000 in Hong Kong.
URI: http://hdl.handle.net/10397/32992
ISSN: 0926-5805
EISSN: 1872-7891
DOI: 10.1016/S0926-5805(01)00067-X
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

5
Last Week
0
Last month
0
Citations as of Aug 13, 2017

Page view(s)

58
Last Week
2
Last month
Checked on Aug 13, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.