Reading handwritten digits: a ZIP code recognition system

A neural network algorithm-based system that reads handwritten ZIP codes appearing on real US mail is described. The system uses a recognition-based segmenter, that is a hybrid of connected-components analysis (CCA), vertical cuts, and a neural network recognizer. Connected components that are singl...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computer (Long Beach, Calif.) Calif.), 1992-07, Vol.25 (7), p.59-63
Hauptverfasser:	Matan, O., Baird, H.S., Bromley, J., Burges, C.J.C., Denker, J.S., Jackel, L.D., Le Cun, Y., Pednault, E.P.D., Satterfield, W.D., Stenard, C.E., Thompson, T.J.
Format:	Artikel
Sprache:	eng
Schlagworte:	Character recognition Handwriting recognition Image processing Image recognition Information systems Laboratories Man machine systems Pattern recognition Research and development Robustness
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!