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

Yu, Fengchang; Lu, Wei

Permalink

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

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

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

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