Context-Sensitive Error Correction: Using Topic Models to Improve OCR

Modern optical, character recognition software relies on human interaction to correct mis recognized characters. Even though the software often reliably identifies low-confidence output, the simple language and vocabulary models employed are insufficient to automatically correct mistakes. This paper...

Full description

Saved in:
Bibliographic Details
Main Authors: Wick, M.L., Ross, M.G., Learned-Miller, E.G.
Format: Conference Proceeding
Language:English
Subjects:
Character recognition
Context modeling
Error correction
Frequency
Hidden Markov models
Humans
Linear discriminant analysis
Optical character recognition software
Tongue
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Modern optical, character recognition software relies on human interaction to correct mis recognized characters. Even though the software often reliably identifies low-confidence output, the simple language and vocabulary models employed are insufficient to automatically correct mistakes. This paper demonstrates that topic models, which automatically detect and represent an article's semantic context, reduces error by 7% over a global word distribution in a simulated OCR correction task. Detecting and leveraging context in this manner is an important step towards improving OCR.
ISSN:1520-5363
2379-2140
DOI:10.1109/ICDAR.2007.4377099