Style-Based Ballot Mark Recognition

Pingping Xiu; Daniel Lopresti; Henry Baird; George Nagy; Elisa Barney Smith

doi:10.1109/ICDAR.2009.273

Style-Based Ballot Mark Recognition

Pingping Xiu
, Daniel Lopresti
, Henry Baird
, George Nagy
, Elisa Barney Smith

Electrical Engineering Department

Research output: Contribution to journal › Article › peer-review

12 Scopus citations

1 Downloads (Pure)

Abstract

The push toward voting via hand-marked paper ballots has focused attention on the limitations of current optical scan systems. Discrepancies between human and machine interpretations of ballot markings can lead to a loss of trust in the election process. In this paper, a style-based approach to ballot recognition is proposed in which marks are recognized collectively rather than in isolation. The consistency of a voter’s style is leveraged to improve the overall accuracy of the system. We compare style-based recognition to various kinds of singlet classifiers and show that it outperforms them by a substantial margin

Original language	American English
Journal	10th International Conference on Document Analysis and Recognition, 2009. ICDAR '09.
DOIs	https://doi.org/10.1109/ICDAR.2009.273
State	Published - 1 Jul 2009

Keywords

optical character recognition
pattern classification
public administration

EGS Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/ICDAR.2009.273License: Unspecified

Style-Based Ballot Mark RecognitionFinal published version, 389 KBLicense: Unspecified

Cite this

@article{24036de91a784b9c81d52f1a52e099b3,

title = "Style-Based Ballot Mark Recognition",

abstract = " The push toward voting via hand-marked paper ballots has focused attention on the limitations of current optical scan systems. Discrepancies between human and machine interpretations of ballot markings can lead to a loss of trust in the election process. In this paper, a style-based approach to ballot recognition is proposed in which marks are recognized collectively rather than in isolation. The consistency of a voter{\textquoteright}s style is leveraged to improve the overall accuracy of the system. We compare style-based recognition to various kinds of singlet classifiers and show that it outperforms them by a substantial margin",

keywords = "optical character recognition, pattern classification, public administration",

author = "Pingping Xiu and Daniel Lopresti and Henry Baird and George Nagy and \{Barney Smith\}, Elisa",

year = "2009",

month = jul,

day = "1",

doi = "10.1109/ICDAR.2009.273",

language = "American English",

}

TY - JOUR

T1 - Style-Based Ballot Mark Recognition

AU - Xiu, Pingping

AU - Lopresti, Daniel

AU - Baird, Henry

AU - Nagy, George

AU - Barney Smith, Elisa

PY - 2009/7/1

Y1 - 2009/7/1

N2 - The push toward voting via hand-marked paper ballots has focused attention on the limitations of current optical scan systems. Discrepancies between human and machine interpretations of ballot markings can lead to a loss of trust in the election process. In this paper, a style-based approach to ballot recognition is proposed in which marks are recognized collectively rather than in isolation. The consistency of a voter’s style is leveraged to improve the overall accuracy of the system. We compare style-based recognition to various kinds of singlet classifiers and show that it outperforms them by a substantial margin

AB - The push toward voting via hand-marked paper ballots has focused attention on the limitations of current optical scan systems. Discrepancies between human and machine interpretations of ballot markings can lead to a loss of trust in the election process. In this paper, a style-based approach to ballot recognition is proposed in which marks are recognized collectively rather than in isolation. The consistency of a voter’s style is leveraged to improve the overall accuracy of the system. We compare style-based recognition to various kinds of singlet classifiers and show that it outperforms them by a substantial margin

KW - optical character recognition

KW - pattern classification

KW - public administration

UR - https://scholarworks.boisestate.edu/electrical_facpubs/44

U2 - 10.1109/ICDAR.2009.273

DO - 10.1109/ICDAR.2009.273

M3 - Article

JO - 10th International Conference on Document Analysis and Recognition, 2009. ICDAR '09.

JF - 10th International Conference on Document Analysis and Recognition, 2009. ICDAR '09.

ER -

Style-Based Ballot Mark Recognition

Abstract

Keywords

EGS Disciplines

Access to Document

Other files and links

Fingerprint

Cite this