3 April 1997 Automated system for numerically rating document image quality
Author Affiliations +
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.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
T. Michael Cannon, T. Michael Cannon, Patrick M. Kelly, Patrick M. Kelly, S. Sitharama Iyengar, S. Sitharama Iyengar, Nathan Brener, Nathan Brener, "Automated system for numerically rating document image quality", Proc. SPIE 3027, Document Recognition IV, (3 April 1997); doi: 10.1117/12.270068; https://doi.org/10.1117/12.270068


Image quality metrics applied to digital pathology
Proceedings of SPIE (April 28 2016)
Keyword spotting via word shape recognition
Proceedings of SPIE (March 29 1995)
Key-text spotting in documentary videos using Adaboost
Proceedings of SPIE (February 16 2006)
Federal Register document image database
Proceedings of SPIE (January 06 1999)

Back to Top