Versatile Text Extraction System for Text-to-Speech Reading Assistant Camera

Hideaki Goto

doi:10.3233/978-1-61499-566-1-392

Versatile Text Extraction System for Text-to-Speech Reading Assistant Camera

Hideaki Goto

Research and Development Divisions

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

Abstract

Wearable camera device translating the text in the scene into speech is one of the most anticipated devices for the visually-impaired. The users would probably want to read any text using such a device. Although various scene text extraction methods have been developed so far, the target objects are most often limited to simple signboards, small memos, etc. We propose a versatile scene text extraction method that can handle a wide variety of targets including complex signboards with many text lines. Experimental results show that our system runs at a video rate and can extract densely arranged text lines even with some distortion and shading. A locally-adaptive binarization technique contributes to the better quality of extracted text images.

Original language	English
Title of host publication	Assistive Technology
Subtitle of host publication	Building Bridges
Editors	Cecilia Sik-Lanyi, Peter Cudd, Klaus Miesenberger, Evert-Jan Hoogerwerf
Publisher	IOS Press
Pages	392-397
Number of pages	6
ISBN (Electronic)	9781614995654
DOIs	https://doi.org/10.3233/978-1-61499-566-1-392
Publication status	Published - 2015 Jan 1
Event	13th European Conference on the Advancement of Assistive Technology, AAATE 2015 - Budapest, Hungary Duration: 2015 Sept 9 → 2015 Sept 12

Publication series

Name	Studies in Health Technology and Informatics
Volume	217
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Other

Other	13th European Conference on the Advancement of Assistive Technology, AAATE 2015
Country/Territory	Hungary
City	Budapest
Period	15/9/9 → 15/9/12

Keywords

reading assistant
scene text recognition
text-to-speech
versatile text extraction
wearable camera

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/978-1-61499-566-1-392

Cite this

Versatile Text Extraction System for Text-to-Speech Reading Assistant Camera. / Goto, Hideaki.

Assistive Technology: Building Bridges. ed. / Cecilia Sik-Lanyi; Peter Cudd; Klaus Miesenberger; Evert-Jan Hoogerwerf. IOS Press, 2015. p. 392-397 (Studies in Health Technology and Informatics; Vol. 217).

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

Goto, H 2015, Versatile Text Extraction System for Text-to-Speech Reading Assistant Camera. in C Sik-Lanyi, P Cudd, K Miesenberger & E-J Hoogerwerf (eds), Assistive Technology: Building Bridges. Studies in Health Technology and Informatics, vol. 217, IOS Press, pp. 392-397, 13th European Conference on the Advancement of Assistive Technology, AAATE 2015, Budapest, Hungary, 15/9/9. https://doi.org/10.3233/978-1-61499-566-1-392

@inproceedings{6a2ef2d1203e4527a21a91eaca5ad852,

title = "Versatile Text Extraction System for Text-to-Speech Reading Assistant Camera",

abstract = "Wearable camera device translating the text in the scene into speech is one of the most anticipated devices for the visually-impaired. The users would probably want to read any text using such a device. Although various scene text extraction methods have been developed so far, the target objects are most often limited to simple signboards, small memos, etc. We propose a versatile scene text extraction method that can handle a wide variety of targets including complex signboards with many text lines. Experimental results show that our system runs at a video rate and can extract densely arranged text lines even with some distortion and shading. A locally-adaptive binarization technique contributes to the better quality of extracted text images.",

keywords = "reading assistant, scene text recognition, text-to-speech, versatile text extraction, wearable camera",

author = "Hideaki Goto",

year = "2015",

month = jan,

day = "1",

doi = "10.3233/978-1-61499-566-1-392",

language = "English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "392--397",

editor = "Cecilia Sik-Lanyi and Peter Cudd and Klaus Miesenberger and Evert-Jan Hoogerwerf",

booktitle = "Assistive Technology",

address = "Netherlands",

note = "13th European Conference on the Advancement of Assistive Technology, AAATE 2015 ; Conference date: 09-09-2015 Through 12-09-2015",

}

TY - GEN

T1 - Versatile Text Extraction System for Text-to-Speech Reading Assistant Camera

AU - Goto, Hideaki

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Wearable camera device translating the text in the scene into speech is one of the most anticipated devices for the visually-impaired. The users would probably want to read any text using such a device. Although various scene text extraction methods have been developed so far, the target objects are most often limited to simple signboards, small memos, etc. We propose a versatile scene text extraction method that can handle a wide variety of targets including complex signboards with many text lines. Experimental results show that our system runs at a video rate and can extract densely arranged text lines even with some distortion and shading. A locally-adaptive binarization technique contributes to the better quality of extracted text images.

AB - Wearable camera device translating the text in the scene into speech is one of the most anticipated devices for the visually-impaired. The users would probably want to read any text using such a device. Although various scene text extraction methods have been developed so far, the target objects are most often limited to simple signboards, small memos, etc. We propose a versatile scene text extraction method that can handle a wide variety of targets including complex signboards with many text lines. Experimental results show that our system runs at a video rate and can extract densely arranged text lines even with some distortion and shading. A locally-adaptive binarization technique contributes to the better quality of extracted text images.

KW - reading assistant

KW - scene text recognition

KW - text-to-speech

KW - versatile text extraction

KW - wearable camera

UR - http://www.scopus.com/inward/record.url?scp=84952041947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84952041947&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-566-1-392

DO - 10.3233/978-1-61499-566-1-392

M3 - Conference contribution

C2 - 26294503

AN - SCOPUS:84952041947

T3 - Studies in Health Technology and Informatics

SP - 392

EP - 397

BT - Assistive Technology

A2 - Sik-Lanyi, Cecilia

A2 - Cudd, Peter

A2 - Miesenberger, Klaus

A2 - Hoogerwerf, Evert-Jan

PB - IOS Press

T2 - 13th European Conference on the Advancement of Assistive Technology, AAATE 2015

Y2 - 9 September 2015 through 12 September 2015

ER -

Versatile Text Extraction System for Text-to-Speech Reading Assistant Camera

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this