Ballot Mark Detection

Elisa H. Barney Smith; Daniel Lopresti; George Nagy

doi:10.1109/ICPR.2008.4761549

Ballot Mark Detection

Elisa H. Barney Smith, Daniel Lopresti, George Nagy

Electrical Engineering Department

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

Abstract

Optical mark sensing, i.e., detecting whether a "bubble" has been filled in, may seem straightforward. However, on US election ballots the shape, intensity, size and position of the marks, while specified, are highly variable due to a diverse electorate. The ballots may be produced and scanned by poorly maintained equipment. Yet near-perfect results are required. To improve the current technology, which has been subject to criticism, components of a process for identifying marks on an optical sense ballot are evaluated. When marked synthetic ballots are compared to an unmarked ballot, the absolute difference of adaptive thresholded images gives best detection rates for all darknesses of marks, but at a false alarm rate increase. Simple absolute differencing can give good detection results with lower false alarm rates.

Original language	American English
Journal	International Conference on Pattern Recognition
DOIs	https://doi.org/10.1109/ICPR.2008.4761549
State	Published - 1 Dec 2008

Keywords

government data processing
image colour analysis
image segmentation
object detection
politics

EGS Disciplines

Computer Engineering

Access to Document

10.1109/ICPR.2008.4761549License: Unspecified

Ballot Mark DetectionFinal published version, 247 KBLicense: Unspecified

Cite this

@article{1d74122bb2e94931999ecfb2ce0e4a42,

title = "Ballot Mark Detection",

abstract = " Optical mark sensing, i.e., detecting whether a {"}bubble{"} has been filled in, may seem straightforward. However, on US election ballots the shape, intensity, size and position of the marks, while specified, are highly variable due to a diverse electorate. The ballots may be produced and scanned by poorly maintained equipment. Yet near-perfect results are required. To improve the current technology, which has been subject to criticism, components of a process for identifying marks on an optical sense ballot are evaluated. When marked synthetic ballots are compared to an unmarked ballot, the absolute difference of adaptive thresholded images gives best detection rates for all darknesses of marks, but at a false alarm rate increase. Simple absolute differencing can give good detection results with lower false alarm rates.",

keywords = "government data processing, image colour analysis, image segmentation, object detection, politics",

author = "{Barney Smith}, {Elisa H.} and Daniel Lopresti and George Nagy",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/ICPR.2008.4761549",

language = "American English",

}

TY - JOUR

T1 - Ballot Mark Detection

AU - Barney Smith, Elisa H.

AU - Lopresti, Daniel

AU - Nagy, George

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Optical mark sensing, i.e., detecting whether a "bubble" has been filled in, may seem straightforward. However, on US election ballots the shape, intensity, size and position of the marks, while specified, are highly variable due to a diverse electorate. The ballots may be produced and scanned by poorly maintained equipment. Yet near-perfect results are required. To improve the current technology, which has been subject to criticism, components of a process for identifying marks on an optical sense ballot are evaluated. When marked synthetic ballots are compared to an unmarked ballot, the absolute difference of adaptive thresholded images gives best detection rates for all darknesses of marks, but at a false alarm rate increase. Simple absolute differencing can give good detection results with lower false alarm rates.

AB - Optical mark sensing, i.e., detecting whether a "bubble" has been filled in, may seem straightforward. However, on US election ballots the shape, intensity, size and position of the marks, while specified, are highly variable due to a diverse electorate. The ballots may be produced and scanned by poorly maintained equipment. Yet near-perfect results are required. To improve the current technology, which has been subject to criticism, components of a process for identifying marks on an optical sense ballot are evaluated. When marked synthetic ballots are compared to an unmarked ballot, the absolute difference of adaptive thresholded images gives best detection rates for all darknesses of marks, but at a false alarm rate increase. Simple absolute differencing can give good detection results with lower false alarm rates.

KW - government data processing

KW - image colour analysis

KW - image segmentation

KW - object detection

KW - politics

UR - https://scholarworks.boisestate.edu/electrical_facpubs/16

U2 - 10.1109/ICPR.2008.4761549

DO - 10.1109/ICPR.2008.4761549

M3 - Article

JO - International Conference on Pattern Recognition

JF - International Conference on Pattern Recognition

ER -

Ballot Mark Detection

Abstract

Keywords

EGS Disciplines

Access to Document

Other files and links

Fingerprint

Cite this