Accuracy improvement of character recognition by hexagonal zoning

Wataru Oyama, Akihito Yamamoto, Tetsushi Wakabayashi, Fumitaka Kimura

Research output: Contribution to journalArticle

Abstract

Accurate off-line character recognition is still very important for camera based printed document analysis. Due to its inherent conceptual and technical simplicity, conventional recognition strategies relied on features extracted using square block zoning of a character image. In this paper, we propose an isotropic feature extraction method using regular hexagonal zoning and empirically confirm its effectiveness for printed and handwritten character recognition. We accomplished printed character recognition and handwritten character recognition experiments using large-scale evaluating datasets. The average accuracy was improved by 2% in experiments using gradient features. And the effectiveness of hexagonal zoning for recognition of high stroke count characters and low-resolution characters is confirmed in both printed and handwritten character recognition by the experiments.

Original languageEnglish
Pages (from-to)1824-1831
Number of pages8
JournalIEEJ Transactions on Electronics, Information and Systems
Volume134
Issue number12
DOIs
Publication statusPublished - Jan 1 2014

Fingerprint

Zoning
Character recognition
Experiments
Feature extraction
Cameras

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Accuracy improvement of character recognition by hexagonal zoning. / Oyama, Wataru; Yamamoto, Akihito; Wakabayashi, Tetsushi; Kimura, Fumitaka.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 134, No. 12, 01.01.2014, p. 1824-1831.

Research output: Contribution to journalArticle

Oyama, Wataru ; Yamamoto, Akihito ; Wakabayashi, Tetsushi ; Kimura, Fumitaka. / Accuracy improvement of character recognition by hexagonal zoning. In: IEEJ Transactions on Electronics, Information and Systems. 2014 ; Vol. 134, No. 12. pp. 1824-1831.
@article{56e29ccef56646cca6d36262b1b7f191,
title = "Accuracy improvement of character recognition by hexagonal zoning",
abstract = "Accurate off-line character recognition is still very important for camera based printed document analysis. Due to its inherent conceptual and technical simplicity, conventional recognition strategies relied on features extracted using square block zoning of a character image. In this paper, we propose an isotropic feature extraction method using regular hexagonal zoning and empirically confirm its effectiveness for printed and handwritten character recognition. We accomplished printed character recognition and handwritten character recognition experiments using large-scale evaluating datasets. The average accuracy was improved by 2{\%} in experiments using gradient features. And the effectiveness of hexagonal zoning for recognition of high stroke count characters and low-resolution characters is confirmed in both printed and handwritten character recognition by the experiments.",
author = "Wataru Oyama and Akihito Yamamoto and Tetsushi Wakabayashi and Fumitaka Kimura",
year = "2014",
month = "1",
day = "1",
doi = "10.1541/ieejeiss.134.1824",
language = "English",
volume = "134",
pages = "1824--1831",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "12",

}

TY - JOUR

T1 - Accuracy improvement of character recognition by hexagonal zoning

AU - Oyama, Wataru

AU - Yamamoto, Akihito

AU - Wakabayashi, Tetsushi

AU - Kimura, Fumitaka

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Accurate off-line character recognition is still very important for camera based printed document analysis. Due to its inherent conceptual and technical simplicity, conventional recognition strategies relied on features extracted using square block zoning of a character image. In this paper, we propose an isotropic feature extraction method using regular hexagonal zoning and empirically confirm its effectiveness for printed and handwritten character recognition. We accomplished printed character recognition and handwritten character recognition experiments using large-scale evaluating datasets. The average accuracy was improved by 2% in experiments using gradient features. And the effectiveness of hexagonal zoning for recognition of high stroke count characters and low-resolution characters is confirmed in both printed and handwritten character recognition by the experiments.

AB - Accurate off-line character recognition is still very important for camera based printed document analysis. Due to its inherent conceptual and technical simplicity, conventional recognition strategies relied on features extracted using square block zoning of a character image. In this paper, we propose an isotropic feature extraction method using regular hexagonal zoning and empirically confirm its effectiveness for printed and handwritten character recognition. We accomplished printed character recognition and handwritten character recognition experiments using large-scale evaluating datasets. The average accuracy was improved by 2% in experiments using gradient features. And the effectiveness of hexagonal zoning for recognition of high stroke count characters and low-resolution characters is confirmed in both printed and handwritten character recognition by the experiments.

UR - http://www.scopus.com/inward/record.url?scp=84916631230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84916631230&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.134.1824

DO - 10.1541/ieejeiss.134.1824

M3 - Article

AN - SCOPUS:84916631230

VL - 134

SP - 1824

EP - 1831

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 12

ER -