Training Neural Networks for Reading Handwritten Amounts on Checks
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...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2002
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/699 |
| _version_ | 1826210926945107968 |
|---|---|
| author | Palacios, Rafael Gupta, Amar |
| author_facet | Palacios, Rafael Gupta, Amar |
| author_sort | Palacios, Rafael |
| collection | MIT |
| 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. |
| first_indexed | 2024-09-23T14:57:40Z |
| id | mit-1721.1/699 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:57:40Z |
| publishDate | 2002 |
| record_format | dspace |
| spelling | mit-1721.1/6992019-04-10T21:56:19Z Training Neural Networks for Reading Handwritten Amounts on Checks Palacios, Rafael Gupta, Amar Neural Networks Optical Character Recognition Check Processing Document Imaging Unconstrained Handwritten Numerals 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. 2002-06-07T18:31:17Z 2002-06-07T18:31:17Z 2002-06-07T18:31:26Z http://hdl.handle.net/1721.1/699 en_US MIT Sloan School of Management Working Paper;4365-02 340466 bytes application/pdf application/pdf |
| spellingShingle | Neural Networks Optical Character Recognition Check Processing Document Imaging Unconstrained Handwritten Numerals Palacios, Rafael Gupta, Amar Training Neural Networks for Reading Handwritten Amounts on Checks |
| title | Training Neural Networks for Reading Handwritten Amounts on Checks |
| title_full | Training Neural Networks for Reading Handwritten Amounts on Checks |
| title_fullStr | Training Neural Networks for Reading Handwritten Amounts on Checks |
| title_full_unstemmed | Training Neural Networks for Reading Handwritten Amounts on Checks |
| title_short | Training Neural Networks for Reading Handwritten Amounts on Checks |
| title_sort | training neural networks for reading handwritten amounts on checks |
| topic | Neural Networks Optical Character Recognition Check Processing Document Imaging Unconstrained Handwritten Numerals |
| url | http://hdl.handle.net/1721.1/699 |
| work_keys_str_mv | AT palaciosrafael trainingneuralnetworksforreadinghandwrittenamountsonchecks AT guptaamar trainingneuralnetworksforreadinghandwrittenamountsonchecks |