OCR correction based on document level knowledge

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 5010, Issue , 2003, Pages 103-110

  Nartker, T ^a   Taghva, K ^a   Young, R ^a   Borsack, J ^a   Condit, A ^a  

^a UNIVERSITY OF NEVADA   (United States)

Author keywords

Non stopword accuracy; OCR correction; Retrieval from noisy documents

Indexed keywords

INDEXING (OF INFORMATION); INFORMATION RETRIEVAL SYSTEMS; INFORMATION SCIENCE;

NOISY DOCUMENTS;

OPTICAL CHARACTER RECOGNITION;

EID: 0037718352     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.479681     Document Type: Conference Paper

References (5)

1. Kazem Taghva, Allen Condit, Julie Borsack, John Kilburg, Changshi Wu, and Jeff Gilbreth, "The MANICURE document processing system", Proc. IS&T/SPIE 1998 Intl. Symp. On Electronic Imaging Science and Technology, San Jose, CA, January 1998.
2. Kazem Taghva, Julie Borsack, and Allen Condit, "Evaluation of model-based retrieval effectiveness with OCR text", ACM Transactions on Information Systems, 14(1):63-93, January 1996.
3. Gerald Salton, Automatic Text Processing, Addison-Wesley, New York, 1989.
4. Paul McJones and Andrew Birrell, pstotext, Digital Equipment Corp. Systems Research Center, http://research.compaq.com/SRC/virtualpaper/pstotext.html.
5. Stephen Rice and Thomas Nartker, "The ISRI Analytic Tools for OCR Evaluation", UNLV/Information Science Research Institute, TR-96-02, August 1996.