Using Field Interdependence to Improve Correction Performance in a Transducer-Based OCR Post-Processing System

In an automatic handwritten form processing system it is often necessary to use the lexical or linguistic restrictions present in the field contents in order to obtain acceptable recognition rates. Since each field is known to hold a given kind of information (name, address...), a language model can...

Full description

Saved in:
Bibliographic Details
Main Authors: Perez-Cortes, J, Llobet, Rafael, Navarro-Cerdan, J R, Arlandis, J
Format: Conference Proceeding
Language:English
Subjects:
Cities and towns
Error analysis
Expected Error Rate
Handwriting recognition
Hidden Markov models
Language Model
OCR
Optical character recognition software
Postprocessing
Reject Rate
Stochastic processes
Threshold
Transducers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In an automatic handwritten form processing system it is often necessary to use the lexical or linguistic restrictions present in the field contents in order to obtain acceptable recognition rates. Since each field is known to hold a given kind of information (name, address...), a language model can be defined for it. But, often, in a typical form there are fields linked by known relations, like "Street" and "Postal Code" or "Country" and "City". We have used Weighted Finite-State Transducers (WFSTs) to combine Stochastic Error-Correcting Language Models from different interdependent fields in real handwritten forms and measured the improvements obtained.
DOI:10.1109/ICFHR.2010.99