An automated system for numerically rating document image quality

Conference · Tue Apr 01 00:00:00 EST 1997

OSTI ID:463673

Cannon, M; Kelly, P ^[1]; Iyengar, S S; Brener, N ^[2]

---

1. Los Alamos National Lab., NM (United States)
2. Louisiana State Univ., Baton Rouge, LA (United States)

As part of the Department of Energy document declassification program, the authors have developed a numerical rating system to predict the OCR error rate that they 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.

• Research Organization: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: W-7405-ENG-36
• OSTI ID: 463673
• Report Number(s): LA-UR-97-214; CONF-970231-24; ON: DE97004756; TRN: AHC29709%%110
• Resource Relation: Conference: SPIE international symposium, San Jose, CA (United States), 8-14 Feb 1997; Other Information: PBD: [1997]
• Country of Publication: United States
• Language: English

Related Subjects

99 MATHEMATICS
COMPUTERS
INFORMATION SCIENCE
MANAGEMENT
LAW
MISCELLANEOUS
RECORDS MANAGEMENT
ALGORITHMS
DECLASSIFICATION
OPTICAL EQUIPMENT
ERRORS
IMAGES
PROBABILISTIC ESTIMATION
PHOTOCOPYING
US DOE
ACCURACY
DIGITIZERS
QUALITY CONTROL