Share Email Print

Proceedings Paper

Automated system for numerically rating document image quality
Author(s): T. Michael Cannon; Patrick M. Kelly; S. Sitharama Iyengar; Nathan Brener
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

As part of the Department of Energy document declassification program, we have developed a numerical rating system to predict the OCR error rate that we expect to encounter when processing a particular document. The rating algorithm produces a vector containing scores for different document image attributes such as speckle and touching characters. The OCR error rate for a document is computed from a weighted sum of the elements of the corresponding quality vector. The predicted OCR error rate will be used to screen documents that would not be handled properly with existing document processing products.

Paper Details

Date Published: 3 April 1997
PDF: 7 pages
Proc. SPIE 3027, Document Recognition IV, (3 April 1997); doi: 10.1117/12.270068
Show Author Affiliations
T. Michael Cannon, Los Alamos National Lab. (United States)
Patrick M. Kelly, Los Alamos National Lab. (United States)
S. Sitharama Iyengar, Louisiana State Univ. (United States)
Nathan Brener, Louisiana State Univ. (United States)

Published in SPIE Proceedings Vol. 3027:
Document Recognition IV
Luc M. Vincent; Jonathan J. Hull, Editor(s)

© SPIE. Terms of Use
Back to Top