Training Neural Networks for Reading Handwritten Amounts on Checks

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/699

Full metadata record

DC Field	Value	Language
dc.creator	Gupta, Amar	-
dc.creator	Palacios, Rafael	-
dc.date	2002-06-07T18:31:17Z	-
dc.date	2002-06-07T18:31:17Z	-
dc.date	2002-06-07T18:31:26Z	-
dc.date.accessioned	2013-05-31T14:12:06Z	-
dc.date.available	2013-05-31T14:12:06Z	-
dc.date.issued	2013-05-31	-
dc.identifier	http://hdl.handle.net/1721.1/699	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/jspui/handle/1721	-
dc.description	While reading handwritten text accurately is a difficult task for computers, the conversion of handwritten papers into digital format is necessary for automatic processing. Since most bank checks are handwritten, the number of checks is very high, and manual processing involves significant expenses, many banks are interested in systems that can read check automatically. This paper presents several approaches to improve the accuracy of neural networks used to read unconstrained numerals in the courtesy amount field of bank checks.	-
dc.format	340466 bytes	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	MIT Sloan School of Management Working Paper;4365-02	-
dc.subject	Optical Character Recognition	-
dc.subject	Unconstrained Handwritten Numerals	-
dc.subject	Check Processing	-
dc.subject	Document Imaging	-
dc.subject	Neural Networks	-
dc.title	Training Neural Networks for Reading Handwritten Amounts on Checks	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI