Graph-based keyword spotting in historical manuscripts using Hausdorff edit distance

Reza Ameri, Mohammad (Concordia University, Computer Science and Software Engineering Department, Montréal, Canada) ; Stauffer, Michael (University of Applied Sciences and Arts Northwestern Switzerland, Institute for Information Systems, Olten, Switzerland ; University of Pretoria, Pretoria, South Africa) ; Riesen, Kaspar (University of Applied Sciences and Arts Northwestern Switzerland, Institute for Information Systems, Olten, Switzerland) ; Bui, Tien D. (Concordia University, Computer Science and Software Engineering Department, Montréal, Canada) ; Fischer, Andreas (School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland ; Department of Informatics, University of Fribourg, Fribourg, Switzerland)

Keyword spotting enables content-based retrieval of scanned historical manuscripts using search terms, which, in turn, facilitates the indexation in digital libraries. Recent approaches include graph-based representations that capture the complex structure of handwriting. However, the high representational power of graphs comes at the cost of high computational complexity for graph matching. In this article, we investigate the potential of Hausdorff edit distance (HED) for keyword spotting. It is an efficient quadratictime approximation of the graph edit distance. In a comprehensive experimental evaluation with four types of handwriting graphs and four benchmark datasets (George Washington, Parzival, Botany, and Alvermann Konzilsprotokolle), we demonstrate a strong performance of the proposed HED-based method when compared with the state of the art, both, in terms of precision and speed.


Keywords:
Article Type:
scientifique
Faculty:
Ingénierie et Architecture
School:
HEIA-FR
Institute:
iCoSys - Institut des systèmes complexes
Subject(s):
Ingénierie
Date:
2018-05
Pagination:
7 p.
Published in:
Pattern Recognition Letters
DOI:
ISSN:
0167-8655
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2019-02-26, last modified 2019-03-05

Fulltext:
Download fulltext
PDF

Rate this document:

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