A voting system for automatic OCR correction

S. Klein, M. Ben-Nissan, M. Kopel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


A new post-processing system for the enhancement of OCR produced text is suggested, which improves automatic data acquisition for large full-text Information Retrieval systems. The idea is to match the output of several OCR devices, thereby detecting possible errors, and to suggest possible corrections based on statistical information and dictionaries. The results of testing the new method on OCRs for several languages are reported.
Original languageAmerican English
Title of host publicationProc. Workshop on Information Retrieval and OCR at SIGIR-02
StatePublished - 2002

Bibliographical note

Place of conference:Finland


Dive into the research topics of 'A voting system for automatic OCR correction'. Together they form a unique fingerprint.

Cite this