CITlab ARGUS for historical handwritten documents : Description of CITlab’s System for the HTRtS 2014 Handwritten Text Recognition Task

Tobias Strauß; Tobias Grüning; Gundram Leifert; Roger Labahn

doi:10.18453/rosdok_id00005817

zum übergeordneten Dokument

Tobias Strauß Tobias Grüning Gundram Leifert Roger Labahn

CITlab ARGUS for historical handwritten documents : Description of CITlab’s System for the HTRtS 2014 Handwritten Text Recognition Task

University of Rostock, Institute of Mathematics, 2014

https://doi.org/10.18453/rosdok_id00005817

Abstract: We describe CITlab’s recognition system for the HTRtS competition attached to the 14. International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. The task comprises the recognition of historical handwritten documents. The core algorithms of our system are based on multidimensional recurrent neural networks (MDRNN) and connectionist temporal classification (CTC). The software modules behind that as well as the basic utility technologies are essentially powered by PLANET’s ARGUS framework for intelligent text recognition and image processing.

Workingpaper Freier Zugang

Titel:

CITlab ARGUS for historical handwritten documents: Description of CITlab’s System for the HTRtS 2014 Handwritten Text Recognition Task

Schriftenreihe:

Preprints aus dem Institut für Mathematik, 14/2

Beteiligte Personen:

Tobias Strauß[VerfasserIn]
	0000-0002-5344-4188
	1136294554
Tobias Grüning[VerfasserIn]
	1181883350
Gundram Leifert[VerfasserIn]
Roger Labahn[VerfasserIn]
	0000-0003-1901-9644
	170999645

Zusammenfassung:

We describe CITlab’s recognition system for the HTRtS competition attached to the 14. International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. The task comprises the recognition of historical handwritten documents. The core algorithms of our system are based on multidimensional recurrent neural networks (MDRNN) and connectionist temporal classification (CTC). The software modules behind that as well as the basic utility technologies are essentially powered by PLANET’s ARGUS framework for intelligent text recognition and image processing. [Englisch]

Dokumenttyp:

Workingpaper

Einrichtung:

Mathematisch-Naturwissenschaftliche Fakultät

Sprache:

Englisch

Sachgruppe der DNB:

510 Mathematik

Umfang:

1 Online-Ressource (8 Seiten)

Veröffentlichung /
Entstehung:

Rostock: University of Rostock, Institute of Mathematics