The effects of OCR error on the extraction of private information

Authors:
Kazem Taghva;Russell Beckley;Jeffrey Coombs
Affiliations:
Information Science Research Institute, University of Nevada, Las Vegas;Information Science Research Institute, University of Nevada, Las Vegas;Information Science Research Institute, University of Nevada, Las Vegas
Venue:
DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
Year:
2006

Citing 6
Cited 3

Fundamentals of speech recognition

Fundamentals of speech recognition
Information Extraction: Techniques and Challenges

SCIE '97 International Summer School on Information Extraction: A Multidisciplinary Approach to an Emerging Information Technology
Named entity extraction from noisy input: speech and OCR

ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Information access in the presence of OCR errors

Proceedings of the 1st ACM workshop on Hardcopy document processing
Mining knowledge from text using information extraction

ACM SIGKDD Explorations Newsletter - Natural language processing and text mining
Statistics for Engineering and the Sciences (5th Edition)

Statistics for Engineering and the Sciences (5th Edition)

Review article: A review of structured document retrieval (SDR) technology to improve information access performance in engineering document management

Computers in Industry
Name extraction and formal concept analysis

ICCS'11 Proceedings of the 19th international conference on Conceptual structures for discovering knowledge
Performing information extraction to improve OCR error detection in semi-structured historical documents

Proceedings of the 2011 Workshop on Historical Document Imaging and Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

OCR error has been shown not to affect the average accuracy of text retrieval or text categorization.Recent studies however have indicated that information extraction is significantly degraded by OCR error. We experimented with information extraction software on two collections, one with OCR-ed documents and another with manually-corrected versions of the former. We discovered a significant reduction in accuracy on the OCR text versus the corrected text. The majority of errors were attributable to zoning problems rather than OCR classification errors.