Table information extraction and structure recognition using query patterns
Authors:
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1086-1090
Abstract
In this paper, we present a query-based approach to selectively extract tabular information and recognize the table structure from scanned documents. Unlike conventional table processing paradigms, we adopt a client-driven approach where clients provide a query pattern by specifying a set of key-fields in the document image. The query pattern is first transformed into an attributed relational graph where each node is described with features and the edges with spatial relationships between the nodes. A fast graph matching technique is then used to retrieve other similar graphs from the document image. Further, the extracted graphs are collectively analyzed to deduce the overall tabular structure. Experiments on a dataset of 101 commercial transaction documents demonstrate the effectiveness of the proposed method.Keywords
This publication has 11 references indexed in Scilit:
- A Model Based Framework for Table Processing in Degraded Document Images2013
- Learning to Detect Tables in Scanned Document Images Using Line Information2013
- ICDAR 2013 Table Competition2013
- Document Information Extraction and Its Evaluation Based on Client's Relevance2013
- A simple and effective table detection system from document imagesInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- A constraint-based approach to table structure derivation2005
- ICDAR 2003 robust reading competitions2005
- A retargetable table reader2002
- Three approaches to "industrial" table spotting2002
- Precise Table Recognition by Making Use of Reference Tables1999