Abstract
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 In this paper, we focus on this question by conducting a cross-evaluation experiment on four handwritten historical documents.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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
BP has been introduced in [9].
- 2.
HED has been introduced in [4].
- 3.
George Washington Papers at the Library of Congress, 1741–1799: Series 2, Letterbook 1, pp. 270–279 & 300–309, http://memory.loc.gov/ammem/gwhtml/gwseries2.html.
- 4.
Parzival at IAM historical document database, http://www.fki.inf.unibe.ch/databases/iam-historical-document-database/parzival-database.
- 5.
Alvermann Konzilsprotokolle and Botany at ICFHR2016 benchmark database, http://www.prhlt.upv.es/contests/icfhr2016-kws/data.html.
- 6.
Note that the resulting graphs are available under http://www.histograph.ch/.
References
Ameri, M.R., Stauffer, M., Riesen, K., Bui, T.D., Fischer, A.: Graph-based keyword spotting in historical manuscripts using Hausdorff edit distance. Pattern Recognit. Lett. (2018, in press)
Bui, Q.A., Visani, M., Mullot, R.: Unsupervised word spotting using a graph representation based on invariants. In: International Conference on Document Analysis and Recognition, pp. 616–620. IEEE (2015)
Fischer, A., Keller, A., Frinken, V., Bunke, H.: Lexicon-free handwritten word spotting using character HMMs. Pattern Recognit. Lett. 33(7), 934–942 (2012)
Fischer, A., Suen, C.Y., Frinken, V., Riesen, K., Bunke, H.: Approximation of graph edit distance based on Hausdorff matching. Pattern Recognit. 48(2), 331–343 (2015)
Manmatha, R., Han, C., Riseman, E.: Word spotting: a new approach to indexing handwriting. In: Computer Society Conference on Computer Vision and Pattern Recognition, pp. 631–637. IEEE (1996)
Pratikakis, I., Zagoris, K., Gatos, B., Puigcerver, J., Toselli, A.H., Vidal, E.: ICFHR2016 handwritten keyword spotting competition (H-KWS 2016). In: International Conference on Frontiers in Handwriting Recognition, pp. 613–618. IEEE (2016)
Riba, P., Fischer, A., Lladós, J., Fornés, A.: Learning graph distances with message passing neural networks. In: International Conference on Pattern Recognition. IEEE (2018)
Riba, P., Lladós, J., Fornés, A.: Handwritten word spotting by inexact matching of grapheme graphs. In: International Conference on Document Analysis and Recognition, pp. 781–785. IEEE (2015)
Riesen, K., Bunke, H.: Approximate graph edit distance computation by means of bipartite graph matching. Image Vis. Comput. 27(7), 950–959 (2009)
Stauffer, M., Fischer, A., Riesen, K.: A novel graph database for handwritten word images. In: Robles-Kelly, A., Loog, M., Biggio, B., Escolano, F., Wilson, R. (eds.) S+SSPR 2016. LNCS, vol. 10029, pp. 553–563. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49055-7_49
Stauffer, M., Fischer, A., Riesen, K.: Ensembles for graph-based keyword spotting in historical handwritten documents. In: International Conference on Document Analysis and Recognition, pp. 714–720. IEEE (2017)
Stauffer, M., Fischer, A., Riesen, K.: Keyword spotting in historical handwritten documents based on graph matching. Pattern Recognit. 81, 240–253 (2018)
Wang, P., Eglin, V., Garcia, C., Largeron, C., Lladós, J., Fornés, A.: A novel learning-free word spotting approach based on graph representation. In: International Workshop on Document Analysis Systems, pp. 207–211. IEEE (2014)
Acknowledgements
This work has been supported by the Swiss National Science Foundation project 200021_162852.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Stauffer, M., Maergner, P., Fischer, A., Riesen, K. (2019). Cross-Evaluation of Graph-Based Keyword Spotting in Handwritten Historical Documents. In: Conte, D., Ramel, JY., Foggia, P. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2019. Lecture Notes in Computer Science(), vol 11510. Springer, Cham. https://doi.org/10.1007/978-3-030-20081-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-20081-7_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20080-0
Online ISBN: 978-3-030-20081-7
eBook Packages: Computer ScienceComputer Science (R0)