On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition
Fink GA, Plötz T (2005)
In: Proc. Int. Conf. on Document Analysis and Recognition., 2. Seoul, Korea: IEEE: 1070-1074.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Fink, Gernot A.;
Plötz, Thomas
Einrichtung
Abstract / Bemerkung
Most successful systems for the recognition of unconstrained handwriting currently rely on expert-crafted feature sets that compute local geometric properties from text images. However, by applying appearance based analysis techniques appropriate features could be derived from training data automatically. Therefore, in this paper several different methods for computing appearance based feature representations were investigated and compared to the performance of a state-of-the-art writer-independent recognition system based on geometric features. In extensive experiments promising results were obtained on a challenging recognition task.
Erscheinungsjahr
2005
Titel des Konferenzbandes
Proc. Int. Conf. on Document Analysis and Recognition
Band
2
Seite(n)
1070-1074
Page URI
https://pub.uni-bielefeld.de/record/2618346
Zitieren
Fink GA, Plötz T. On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition. In: Proc. Int. Conf. on Document Analysis and Recognition. Vol 2. Seoul, Korea: IEEE; 2005: 1070-1074.
Fink, G. A., & Plötz, T. (2005). On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition. Proc. Int. Conf. on Document Analysis and Recognition, 2, 1070-1074
Fink, Gernot A., and Plötz, Thomas. 2005. “On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition”. In Proc. Int. Conf. on Document Analysis and Recognition, 2:1070-1074. Seoul, Korea: IEEE.
Fink, G. A., and Plötz, T. (2005). “On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition” in Proc. Int. Conf. on Document Analysis and Recognition, vol. 2, (Seoul, Korea: IEEE), 1070-1074.
Fink, G.A., & Plötz, T., 2005. On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition. In Proc. Int. Conf. on Document Analysis and Recognition. no.2 Seoul, Korea: IEEE, pp. 1070-1074.
G.A. Fink and T. Plötz, “On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition”, Proc. Int. Conf. on Document Analysis and Recognition, vol. 2, Seoul, Korea: IEEE, 2005, pp.1070-1074.
Fink, G.A., Plötz, T.: On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition. Proc. Int. Conf. on Document Analysis and Recognition. 2, p. 1070-1074. IEEE, Seoul, Korea (2005).
Fink, Gernot A., and Plötz, Thomas. “On Appearance-Based Feature Extraction Methods for Writer-Independent Handwritten Text Recognition”. Proc. Int. Conf. on Document Analysis and Recognition. Seoul, Korea: IEEE, 2005.Vol. 2. 1070-1074.