Three dimensional rotation-free camera-based character recognition

Ryo Narita, Wataru Oyama, Tetsushi Wakabayashi, Fumitaka Kimura

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a new method for three dimensional rotation-free recognition of characters in scene. In the proposed method, we employ the Modified Quadratic Discriminant Function (MQDF) classifier trained with samples generated by three dimensional rotation process in a computer. We assume that when recognizing individual characters, considering three dimensional rotation can approximately handle the recognition of characters with perspective distortion. The results of the evaluation experiments using printed alphanumeric characters as an evaluation data set, consisting of approximately 600 samples per class for 62 character classes, show that the recognition rate is 99.34% for rotated characters while it is 99.59% for non rotated characters. We have empirically confirmed that the rotated characters given as the training data set do not negatively affect significantly to recognition of non rotated characters. Moreover, 813 characters extracted from 58 camera-captured scenes were correctly recognized and the feasibility of real world application of our method has been confirmed.

Original languageEnglish
Pages (from-to)876-882
Number of pages7
JournalIEEJ Transactions on Electronics, Information and Systems
Volume133
Issue number4
DOIs
Publication statusPublished - Jan 1 2013

Fingerprint

Character recognition
Cameras
Classifiers
Experiments

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Three dimensional rotation-free camera-based character recognition. / Narita, Ryo; Oyama, Wataru; Wakabayashi, Tetsushi; Kimura, Fumitaka.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 133, No. 4, 01.01.2013, p. 876-882.

Research output: Contribution to journalArticle

Narita, Ryo ; Oyama, Wataru ; Wakabayashi, Tetsushi ; Kimura, Fumitaka. / Three dimensional rotation-free camera-based character recognition. In: IEEJ Transactions on Electronics, Information and Systems. 2013 ; Vol. 133, No. 4. pp. 876-882.
@article{d4f6b3e254734cf3a23629cbdd02b808,
title = "Three dimensional rotation-free camera-based character recognition",
abstract = "In this paper, we propose a new method for three dimensional rotation-free recognition of characters in scene. In the proposed method, we employ the Modified Quadratic Discriminant Function (MQDF) classifier trained with samples generated by three dimensional rotation process in a computer. We assume that when recognizing individual characters, considering three dimensional rotation can approximately handle the recognition of characters with perspective distortion. The results of the evaluation experiments using printed alphanumeric characters as an evaluation data set, consisting of approximately 600 samples per class for 62 character classes, show that the recognition rate is 99.34{\%} for rotated characters while it is 99.59{\%} for non rotated characters. We have empirically confirmed that the rotated characters given as the training data set do not negatively affect significantly to recognition of non rotated characters. Moreover, 813 characters extracted from 58 camera-captured scenes were correctly recognized and the feasibility of real world application of our method has been confirmed.",
author = "Ryo Narita and Wataru Oyama and Tetsushi Wakabayashi and Fumitaka Kimura",
year = "2013",
month = "1",
day = "1",
doi = "10.1541/ieejeiss.133.876",
language = "English",
volume = "133",
pages = "876--882",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "4",

}

TY - JOUR

T1 - Three dimensional rotation-free camera-based character recognition

AU - Narita, Ryo

AU - Oyama, Wataru

AU - Wakabayashi, Tetsushi

AU - Kimura, Fumitaka

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper, we propose a new method for three dimensional rotation-free recognition of characters in scene. In the proposed method, we employ the Modified Quadratic Discriminant Function (MQDF) classifier trained with samples generated by three dimensional rotation process in a computer. We assume that when recognizing individual characters, considering three dimensional rotation can approximately handle the recognition of characters with perspective distortion. The results of the evaluation experiments using printed alphanumeric characters as an evaluation data set, consisting of approximately 600 samples per class for 62 character classes, show that the recognition rate is 99.34% for rotated characters while it is 99.59% for non rotated characters. We have empirically confirmed that the rotated characters given as the training data set do not negatively affect significantly to recognition of non rotated characters. Moreover, 813 characters extracted from 58 camera-captured scenes were correctly recognized and the feasibility of real world application of our method has been confirmed.

AB - In this paper, we propose a new method for three dimensional rotation-free recognition of characters in scene. In the proposed method, we employ the Modified Quadratic Discriminant Function (MQDF) classifier trained with samples generated by three dimensional rotation process in a computer. We assume that when recognizing individual characters, considering three dimensional rotation can approximately handle the recognition of characters with perspective distortion. The results of the evaluation experiments using printed alphanumeric characters as an evaluation data set, consisting of approximately 600 samples per class for 62 character classes, show that the recognition rate is 99.34% for rotated characters while it is 99.59% for non rotated characters. We have empirically confirmed that the rotated characters given as the training data set do not negatively affect significantly to recognition of non rotated characters. Moreover, 813 characters extracted from 58 camera-captured scenes were correctly recognized and the feasibility of real world application of our method has been confirmed.

UR - http://www.scopus.com/inward/record.url?scp=84877774573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877774573&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.133.876

DO - 10.1541/ieejeiss.133.876

M3 - Article

VL - 133

SP - 876

EP - 882

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 4

ER -