A symbolic/neural approach to recognize unconstrained handwritten cursive amounts in bank cheques is proposed. Features like ascenders and descenders are extracted from the binary image of the amount. Depending on the features extracted, some words are recognized entirely symbolically, some words entirely neurally, and the remaining both symbolically and neurally. Results of preliminary experiments are provided.
Symbolic/neural recognition of cursive amounts on bank cheques
01.01.1995
356081 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Symbolic/Neural Recognition of Cursive Amounts on Bank Cheques
British Library Conference Proceedings | 1995
|Cursive Script Recognition Applied to the Processing of Bank Cheques
British Library Conference Proceedings | 1995
|Recognition of Handwritten Month Words on Bank Cheques
British Library Conference Proceedings | 2002
|Recognition of handwritten month words on bank cheques
IEEE | 2002
|