Cross-evaluation of graph-based keyword spotting in handwritten historical documents

Stauffer, Michael (Institute for Information Systems, University of Applied Sciences and Arts Northwestern Switzerland, Olten, Switzerland) ; Maergner, Paul (Department of informatics, University of Fribourg, Fribourg, Switzerland) ; Fischer, Andreas (Department of informatics, University of Fribourg, Fribourg, Switzerland ; School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland) ; Riesen, Kaspar (Institute for Information Systems, University of Applied Sciences and Arts Northwestern Switzerland, Olten, Switzerland)

In contrast to statistical representations, graphs offer some inherent advantages when it comes to handwriting representation. That is, graphs are able to adapt their size and structure to the individual handwriting and represent binary relationships that might exist within the handwriting. We observe an increasing number of graph-based keyword spotting frameworks in the last years. In general, keyword spotting allows to retrieve instances of an arbitrary query in documents. It is common practice to optimise keyword spotting frameworks for each document individually, and thus, the overall generalisability remains somehow questionable. In this paper, we focus on this question by conducting a cross-evaluation experiment on four handwritten historical documents. We observe a direct relationship between parameter settings and the actual handwriting. We also propose different ensemble strategies that allow to keep up with individually optimised systems without a priori knowledge of a certain manuscript. Such a system can potentially be applied to new documents without prior optimisation.


Keywords:
Conference Type:
full paper
Faculty:
Ingénierie et Architecture
School:
HEIA-FR
Institute:
iCoSys - Institut des systèmes complexes
Publisher:
Tours, France, 19-21 June 2019
Date:
2019-06
Tours, France
19-21 June 2019
Pagination:
11 p.
Published in:
Lecture Notes in Computer Science ; Proceedings of 12th IAPR-TC-15 International Workshop, GbRPR 2019: Graph-based representations in pattern recognition, 19-21 June 2019, Tours, France
Numeration (vol. no.):
pp. 45-55
DOI:
ISSN:
0302-9743
ISBN:
978-3-030-20080-0
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2020-01-17, last modified 2020-01-21

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)