Scene Text Recognition Based on Positional Relation between Closed Curves

Yuji Waizumi; Kazuyuki Tanaka

doi:10.1109/AIMS.2014.51

Scene Text Recognition Based on Positional Relation between Closed Curves

Yuji Waizumi, Kazuyuki Tanaka

INF - Applied Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Scene text recognition has attracted much attention in the research community. Many proposed scene text recognition methods adopt a step-by-step procedure, which includes a text extraction phase and a recognition phase. In this study, in order to eliminate the risk of text extraction error, we try to build a scene text recognition system that does not involve the text extraction phase. In our proposed method, an image is viewed as a set of closed curves, and text is extracted and recognized simultaneously from the image by combining the closed curves. Through experiments, we demonstrate the recognition accuracy of our proposed method.

Original language	English
Title of host publication	Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014
Editors	David Al-Dabass, Gregorio Romero, Emilio Corchado, Athanasios Pantelous, Ismail Saad, Alessandra Orsoni
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	182-186
Number of pages	5
ISBN (Electronic)	9781479975990
DOIs	https://doi.org/10.1109/AIMS.2014.51
Publication status	Published - 2014 May 5
Event	2nd IEEE International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014 - Madrid, Spain Duration: 2014 Nov 18 → 2014 Nov 20

Publication series

Name	Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014

Other

Other	2nd IEEE International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014
Country	Spain
City	Madrid
Period	14/11/18 → 14/11/20

Keywords

Gaussian distribution
closed curves
scene text recognition

ASJC Scopus subject areas

Modelling and Simulation
Computer Science(all)

Access to Document

10.1109/AIMS.2014.51

Fingerprint Dive into the research topics of 'Scene Text Recognition Based on Positional Relation between Closed Curves'. Together they form a unique fingerprint.

Cite this

Waizumi, Y., & Tanaka, K. (2014). Scene Text Recognition Based on Positional Relation between Closed Curves. In D. Al-Dabass, G. Romero, E. Corchado, A. Pantelous, I. Saad, & A. Orsoni (Eds.), Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014 (pp. 182-186). [7102457] (Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AIMS.2014.51

Scene Text Recognition Based on Positional Relation between Closed Curves. / Waizumi, Yuji; Tanaka, Kazuyuki.

Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014. ed. / David Al-Dabass; Gregorio Romero; Emilio Corchado; Athanasios Pantelous; Ismail Saad; Alessandra Orsoni. Institute of Electrical and Electronics Engineers Inc., 2014. p. 182-186 7102457 (Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Waizumi, Y & Tanaka, K 2014, Scene Text Recognition Based on Positional Relation between Closed Curves. in D Al-Dabass, G Romero, E Corchado, A Pantelous, I Saad & A Orsoni (eds), Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014., 7102457, Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014, Institute of Electrical and Electronics Engineers Inc., pp. 182-186, 2nd IEEE International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014, Madrid, Spain, 14/11/18. https://doi.org/10.1109/AIMS.2014.51

Waizumi Y, Tanaka K. Scene Text Recognition Based on Positional Relation between Closed Curves. In Al-Dabass D, Romero G, Corchado E, Pantelous A, Saad I, Orsoni A, editors, Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 182-186. 7102457. (Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014). https://doi.org/10.1109/AIMS.2014.51

Waizumi, Yuji ; Tanaka, Kazuyuki. / Scene Text Recognition Based on Positional Relation between Closed Curves. Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014. editor / David Al-Dabass ; Gregorio Romero ; Emilio Corchado ; Athanasios Pantelous ; Ismail Saad ; Alessandra Orsoni. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 182-186 (Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014).

@inproceedings{432534c13a7c4b159b3e5969cf955b57,

title = "Scene Text Recognition Based on Positional Relation between Closed Curves",

abstract = "Scene text recognition has attracted much attention in the research community. Many proposed scene text recognition methods adopt a step-by-step procedure, which includes a text extraction phase and a recognition phase. In this study, in order to eliminate the risk of text extraction error, we try to build a scene text recognition system that does not involve the text extraction phase. In our proposed method, an image is viewed as a set of closed curves, and text is extracted and recognized simultaneously from the image by combining the closed curves. Through experiments, we demonstrate the recognition accuracy of our proposed method.",

keywords = "Gaussian distribution, closed curves, scene text recognition",

author = "Yuji Waizumi and Kazuyuki Tanaka",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE. Copyright: Copyright 2016 Elsevier B.V., All rights reserved.; 2nd IEEE International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014 ; Conference date: 18-11-2014 Through 20-11-2014",

year = "2014",

month = may,

day = "5",

doi = "10.1109/AIMS.2014.51",

language = "English",

series = "Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "182--186",

editor = "David Al-Dabass and Gregorio Romero and Emilio Corchado and Athanasios Pantelous and Ismail Saad and Alessandra Orsoni",

booktitle = "Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014",

}

TY - GEN

T1 - Scene Text Recognition Based on Positional Relation between Closed Curves

AU - Waizumi, Yuji

AU - Tanaka, Kazuyuki

PY - 2014/5/5

Y1 - 2014/5/5

N2 - Scene text recognition has attracted much attention in the research community. Many proposed scene text recognition methods adopt a step-by-step procedure, which includes a text extraction phase and a recognition phase. In this study, in order to eliminate the risk of text extraction error, we try to build a scene text recognition system that does not involve the text extraction phase. In our proposed method, an image is viewed as a set of closed curves, and text is extracted and recognized simultaneously from the image by combining the closed curves. Through experiments, we demonstrate the recognition accuracy of our proposed method.

AB - Scene text recognition has attracted much attention in the research community. Many proposed scene text recognition methods adopt a step-by-step procedure, which includes a text extraction phase and a recognition phase. In this study, in order to eliminate the risk of text extraction error, we try to build a scene text recognition system that does not involve the text extraction phase. In our proposed method, an image is viewed as a set of closed curves, and text is extracted and recognized simultaneously from the image by combining the closed curves. Through experiments, we demonstrate the recognition accuracy of our proposed method.

KW - Gaussian distribution

KW - closed curves

KW - scene text recognition

UR - http://www.scopus.com/inward/record.url?scp=84983103278&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983103278&partnerID=8YFLogxK

U2 - 10.1109/AIMS.2014.51

DO - 10.1109/AIMS.2014.51

M3 - Conference contribution

AN - SCOPUS:84983103278

T3 - Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014

SP - 182

EP - 186

BT - Proceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014

A2 - Al-Dabass, David

A2 - Romero, Gregorio

A2 - Corchado, Emilio

A2 - Pantelous, Athanasios

A2 - Saad, Ismail

A2 - Orsoni, Alessandra

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014

Y2 - 18 November 2014 through 20 November 2014

ER -