Output details
11 - Computer Science and Informatics
University of Birmingham
Output title
Comparing Approaches to Mathematical Document Analysis from PDF
Type
E - Conference contribution
Name of conference/published proceedings
Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR 2011)
Volume number
-
Issue number
-
First page of article
463
ISSN of proceedings
-
Year of publication
2011
URL
-
Number of additional authors
3
Additional information
<17>Our work on recognising and extracting semantics from mathematical formulae in PDF documents has been extended to extracting full text and mathematical content from whole pages of mathematical documents. This makes our system one of only two in the world which have progressed to this capability. In collaboration with Suzuki's Infty group (the other system), this paper gives a formal analysis and comparison based on a new ground truthing of 10 pages from 5 articles. Suzuki is currently taking a critical component of our system to embed as a plug-in into his for improved PDF recognition.
Interdisciplinary
-
Cross-referral requested
-
Research group
A - Artificial Intelligence and Intelligent Robotics
Citation count
1
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
