A neural network-hidden Markov model hybrid for cursive word recognition

We present a neural network-hidden Markov model hybrid for the recognition of cursive words which are represented as left-right sequences of graphemes. The proposed approach models words with ergodic HMMs and is designed for small vocabularies. A single neural network provides grapheme observation p...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Knerr, S., Augustin, E.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Computer networks Concatenated codes Handwriting recognition Hidden Markov models Ink Law Legal factors Neural networks Read only memory Vocabulary
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!