Speedup of Optical Scanner Characterization Subsystem

Roger D. Clements; Elisa H. Barney Smith

doi:10.1117/12.476060

Speedup of Optical Scanner Characterization Subsystem

Roger D. Clements
, Elisa H. Barney Smith

Electrical Engineering Department

Boise State University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Downloads (Pure)

Abstract

Small image deformations such as those introduced by optical scanners significantly reduce the accuracy rate of optical character recognition (OCR) software. Characterization of the scanner used in the OCR process may diminish the impact on recognition rates. Theoretical methods have been developed to characterize a scanner based on the bi-level image resulting from scanning a high contrast document. Two bottlenecks in the naïve implementation of these algorithms have been identified, and techniques were developed to improve the execution time of the software. The algorithms are described and analyzed. Since approximations are used in one of the techniques, the error of the approximations is examined.

Original language	American English
Title of host publication	Proceedings of SPIE
Subtitle of host publication	Document Recognition and Retrieval X
Volume	5010
DOIs	https://doi.org/10.1117/12.476060
State	Published - 2003

Publication series

Name	Proceedings of SPIE

Keywords

image degradation
intensity binarization
point spread function
scanner characterization
synthetic

EGS Disciplines

Electrical and Computer Engineering

Access to Document

10.1117/12.476060License: Unspecified

https://scholarworks.boisestate.edu/electrical_facpubs/93/License: Other

Cite this

@inproceedings{12b10222fc8042cca0067bed91befd96,

title = "Speedup of Optical Scanner Characterization Subsystem",

abstract = " Small image deformations such as those introduced by optical scanners significantly reduce the accuracy rate of optical character recognition (OCR) software. Characterization of the scanner used in the OCR process may diminish the impact on recognition rates. Theoretical methods have been developed to characterize a scanner based on the bi-level image resulting from scanning a high contrast document. Two bottlenecks in the na{\"i}ve implementation of these algorithms have been identified, and techniques were developed to improve the execution time of the software. The algorithms are described and analyzed. Since approximations are used in one of the techniques, the error of the approximations is examined.",

keywords = "image degradation, intensity binarization, point spread function, scanner characterization, synthetic",

author = "Clements, \{Roger D.\} and \{Barney Smith\}, \{Elisa H.\}",

year = "2003",

doi = "10.1117/12.476060",

language = "American English",

volume = "5010",

series = "Proceedings of SPIE",

booktitle = "Proceedings of SPIE",

}

TY - GEN

T1 - Speedup of Optical Scanner Characterization Subsystem

AU - Clements, Roger D.

AU - Barney Smith, Elisa H.

PY - 2003

Y1 - 2003

N2 - Small image deformations such as those introduced by optical scanners significantly reduce the accuracy rate of optical character recognition (OCR) software. Characterization of the scanner used in the OCR process may diminish the impact on recognition rates. Theoretical methods have been developed to characterize a scanner based on the bi-level image resulting from scanning a high contrast document. Two bottlenecks in the naïve implementation of these algorithms have been identified, and techniques were developed to improve the execution time of the software. The algorithms are described and analyzed. Since approximations are used in one of the techniques, the error of the approximations is examined.

AB - Small image deformations such as those introduced by optical scanners significantly reduce the accuracy rate of optical character recognition (OCR) software. Characterization of the scanner used in the OCR process may diminish the impact on recognition rates. Theoretical methods have been developed to characterize a scanner based on the bi-level image resulting from scanning a high contrast document. Two bottlenecks in the naïve implementation of these algorithms have been identified, and techniques were developed to improve the execution time of the software. The algorithms are described and analyzed. Since approximations are used in one of the techniques, the error of the approximations is examined.

KW - image degradation

KW - intensity binarization

KW - point spread function

KW - scanner characterization

KW - synthetic

UR - https://www.scopus.com/pages/publications/0038732521

U2 - 10.1117/12.476060

DO - 10.1117/12.476060

M3 - Conference contribution

VL - 5010

T3 - Proceedings of SPIE

BT - Proceedings of SPIE

ER -

Speedup of Optical Scanner Characterization Subsystem

Abstract

Publication series

Keywords

EGS Disciplines

Access to Document

Other files and links

Fingerprint

Cite this