Triage of OCR results using confidence scores

Prateek Sarkar; Henry S. Baird; John Henderson

doi:10.1117/12.450730

18 December 2001 Triage of OCR results using confidence scores

Prateek Sarkar, Henry S. Baird, John Henderson

Proceedings Volume 4670, Document Recognition and Retrieval IX; (2001) https://doi.org/10.1117/12.450730
Event: Electronic Imaging, 2002, San Jose, California, United States

Abstract

We describe a technique for modeling the character recognition accuracy of an OCR system -- treated as a black box -- on a particular page of printed text based on an examination only of the output top-choice character classifications and, for each, a confidence score such as is supplied by many commercial OCR systems. Latent conditional independence (LCI) models perform better on this task, in our experience, than naive uniform thresholding methods. Given a sufficiently large and representative dataset of OCR (errorful) output and manually proofed (correct) text, we can automatically infer LCI models that exhibit a useful degree of reliability. A collaboration between a PARC research group and a Xerox legacy conversion service bureau has demonstrated that such models can significantly improve the productivity of human proofing staff by triaging -- that is, selecting to bypass manual inspection -- pages whose estimated OCR accuracy exceeds a threshold chosen to ensure that a customer-specified per-page accuracy target will be met with sufficient confidence. We report experimental results on over 1400 pages. Our triage software tools are running in production and will be applied to more than 5 million pages of multi-lingual text.

Citation Download Citation

Prateek Sarkar, Henry S. Baird, and John Henderson "Triage of OCR results using confidence scores", Proc. SPIE 4670, Document Recognition and Retrieval IX, (18 December 2001); https://doi.org/10.1117/12.450730

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available