Intelligent Character Recognition (ICR): A Case Study in Ballot Digit Recognition

Research output: Contribution to journalArticle

Abstract

ICR is an emerging technology for the recognition of hand writing (i.e. turning images of handwritten characters into machine readable characters). The reliability of ICR is continuously improving.There are many commercial ICR engines available currently and most of them are capable ofrecognizing free hand writing, hand printed digits (or alphanumerics) and check boxes.This paper reports on a feasibility study to determine the accuracy of widely available commercialICR engines for hand printed digits and check box recognition in ballot papers. The studyconcludes that current ICR engines are sufficiently robust and achieve very high levels of accuracy(i.e. 95-99%). However none of the current ICR engines achieved 100% accuracy level. Our researchsuggests that a combination of ICR engines and improved “voting” strategies could increasethe accuracy rate close to 100%.
LanguageEnglish
Pages27-34
JournalImage Processing and Communications
Volume15
Issue number2
Publication statusPublished - 1 Dec 2010

Fingerprint

Character recognition
Engines

Cite this

@article{7e652b4d43d747f29dba329faab79b2d,
title = "Intelligent Character Recognition (ICR): A Case Study in Ballot Digit Recognition",
abstract = "ICR is an emerging technology for the recognition of hand writing (i.e. turning images of handwritten characters into machine readable characters). The reliability of ICR is continuously improving.There are many commercial ICR engines available currently and most of them are capable ofrecognizing free hand writing, hand printed digits (or alphanumerics) and check boxes.This paper reports on a feasibility study to determine the accuracy of widely available commercialICR engines for hand printed digits and check box recognition in ballot papers. The studyconcludes that current ICR engines are sufficiently robust and achieve very high levels of accuracy(i.e. 95-99{\%}). However none of the current ICR engines achieved 100{\%} accuracy level. Our researchsuggests that a combination of ICR engines and improved “voting” strategies could increasethe accuracy rate close to 100{\%}.",
author = "Joan Condell and Pratheepan Yogarajah and Siobhan Donaghy",
year = "2010",
month = "12",
day = "1",
language = "English",
volume = "15",
pages = "27--34",
number = "2",

}

Intelligent Character Recognition (ICR): A Case Study in Ballot Digit Recognition. / Condell, Joan; Yogarajah, Pratheepan; Donaghy, Siobhan.

Vol. 15, No. 2, 01.12.2010, p. 27-34.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Intelligent Character Recognition (ICR): A Case Study in Ballot Digit Recognition

AU - Condell, Joan

AU - Yogarajah, Pratheepan

AU - Donaghy, Siobhan

PY - 2010/12/1

Y1 - 2010/12/1

N2 - ICR is an emerging technology for the recognition of hand writing (i.e. turning images of handwritten characters into machine readable characters). The reliability of ICR is continuously improving.There are many commercial ICR engines available currently and most of them are capable ofrecognizing free hand writing, hand printed digits (or alphanumerics) and check boxes.This paper reports on a feasibility study to determine the accuracy of widely available commercialICR engines for hand printed digits and check box recognition in ballot papers. The studyconcludes that current ICR engines are sufficiently robust and achieve very high levels of accuracy(i.e. 95-99%). However none of the current ICR engines achieved 100% accuracy level. Our researchsuggests that a combination of ICR engines and improved “voting” strategies could increasethe accuracy rate close to 100%.

AB - ICR is an emerging technology for the recognition of hand writing (i.e. turning images of handwritten characters into machine readable characters). The reliability of ICR is continuously improving.There are many commercial ICR engines available currently and most of them are capable ofrecognizing free hand writing, hand printed digits (or alphanumerics) and check boxes.This paper reports on a feasibility study to determine the accuracy of widely available commercialICR engines for hand printed digits and check box recognition in ballot papers. The studyconcludes that current ICR engines are sufficiently robust and achieve very high levels of accuracy(i.e. 95-99%). However none of the current ICR engines achieved 100% accuracy level. Our researchsuggests that a combination of ICR engines and improved “voting” strategies could increasethe accuracy rate close to 100%.

M3 - Article

VL - 15

SP - 27

EP - 34

IS - 2

ER -