University of Illinois Urbana-Champaign

A novel computer vision based method for PDF academic literature structure understanding

Yu, Fengchang; Lu, Wei

Content Files
Yu_Lu_Poster.doc

Permalink

https://hdl.handle.net/2142/103374

Description

Title
A novel computer vision based method for PDF academic literature structure understanding
Author(s)
  • Yu, Fengchang
  • Lu, Wei
Issue Date
2019-03-15
Keyword(s)
  • PDF
  • Academic literature
  • Computer vision
  • Structure understanding
Date of Ingest
2019-03-22T21:34:51Z
Abstract
The PDF format plays a crucial role in the field of electronic academic literature publishing, but due to its complicated technical rules, PDF cannot be directly read by machines, which has caused a lot of inconvenience to the research work on academic literature. This poster proposes a computer vision-based PDF document structure understanding method. This method maps visual objects and text objects in PDF academic papers and obtains geometric and text attributes of content objects, supplemented by a heuristic algorithm. The algorithm performs type classification on the content object to obtain the physical structure and logical structure of the PDF document. This method overcomes the shortcomings of other PDF analysis methods that require a large number of artificial feature construction or large-scale corpus training, difficult to identify formula tables, and success-fully constructs a structure understanding and full-text extraction of ACM's collections.
Publisher
iSchools
Series/Report Name or Number
iConference 2019 Proceedings
Type of Resource
text
Genre of Resource
Conference Poster
Language
eng
Permalink
http://hdl.handle.net/2142/103374
DOI
https://doi.org/10.21900/iconf.2019.103374
Copyright and License Information
Copyright 2019 Fengchang Yu and Wei Lu

Owning Collections

iConference 2019 Poster Descriptions PRIMARY