Development of Vertical Text Interpreter for Natural Scene Images

Automatic text recognition in natural scene images is essential for accessing information and understanding our surroundings. Scene text orientations include horizontal scene texts, arbitrarily oriented scene texts, curved scene texts, and vertically oriented scene texts. While attention has been gi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ong Yi Ling, Lau Bee Theng, Almon Chai Weiyen, Christopher Mccarthy
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Deep learning scene text detection scene text recognition shared convolution vertical text interpreter Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/35cbd862fb13404c9f4c024f90235616
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:35cbd862fb13404c9f4c024f90235616
record_format	dspace
spelling	oai:doaj.org-article:35cbd862fb13404c9f4c024f902356162021-11-13T00:00:59ZDevelopment of Vertical Text Interpreter for Natural Scene Images2169-353610.1109/ACCESS.2021.3121608https://doaj.org/article/35cbd862fb13404c9f4c024f902356162021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9580909/https://doaj.org/toc/2169-3536Automatic text recognition in natural scene images is essential for accessing information and understanding our surroundings. Scene text orientations include horizontal scene texts, arbitrarily oriented scene texts, curved scene texts, and vertically oriented scene texts. While attention has been given to horizontal, arbitrarily oriented, and curved text, limited research has been carried out on vertically oriented scene text recognition. To this end, we propose Vertical Text Interpreter, an autonomous vertically oriented scene text recognizer model. Vertical Text Interpreter detects and recognizes vertically oriented scene texts in natural scenes, including vertically-stacked texts, bottom-to-top vertical texts, and top-to-bottom vertical texts. It consists of a shared convolutional neural network, a Vertical Text Spotter, and a Vertical Text Reader. We developed a dataset, namely Vertically Oriented Scene Text 1250 Dataset, created as part of this research, addressing the need for a dataset for this category of scene texts. The performance of the Vertical Text Interpreter is evaluated using benchmark datasets and the VOST-1250 dataset. Results show that Vertical Text Interpreter can detect and recognize different types of vertically oriented scene texts simultaneously. For future work, we can explore Vertical Text Interpreter for the contexts such as reading assistance and visual navigation systems.Ong Yi LingLau Bee ThengAlmon Chai WeiyenChristopher MccarthyIEEEarticleDeep learningscene text detectionscene text recognitionshared convolutionvertical text interpreterElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 144341-144351 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning scene text detection scene text recognition shared convolution vertical text interpreter Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep learning scene text detection scene text recognition shared convolution vertical text interpreter Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ong Yi Ling Lau Bee Theng Almon Chai Weiyen Christopher Mccarthy Development of Vertical Text Interpreter for Natural Scene Images
description	Automatic text recognition in natural scene images is essential for accessing information and understanding our surroundings. Scene text orientations include horizontal scene texts, arbitrarily oriented scene texts, curved scene texts, and vertically oriented scene texts. While attention has been given to horizontal, arbitrarily oriented, and curved text, limited research has been carried out on vertically oriented scene text recognition. To this end, we propose Vertical Text Interpreter, an autonomous vertically oriented scene text recognizer model. Vertical Text Interpreter detects and recognizes vertically oriented scene texts in natural scenes, including vertically-stacked texts, bottom-to-top vertical texts, and top-to-bottom vertical texts. It consists of a shared convolutional neural network, a Vertical Text Spotter, and a Vertical Text Reader. We developed a dataset, namely Vertically Oriented Scene Text 1250 Dataset, created as part of this research, addressing the need for a dataset for this category of scene texts. The performance of the Vertical Text Interpreter is evaluated using benchmark datasets and the VOST-1250 dataset. Results show that Vertical Text Interpreter can detect and recognize different types of vertically oriented scene texts simultaneously. For future work, we can explore Vertical Text Interpreter for the contexts such as reading assistance and visual navigation systems.
format	article
author	Ong Yi Ling Lau Bee Theng Almon Chai Weiyen Christopher Mccarthy
author_facet	Ong Yi Ling Lau Bee Theng Almon Chai Weiyen Christopher Mccarthy
author_sort	Ong Yi Ling
title	Development of Vertical Text Interpreter for Natural Scene Images
title_short	Development of Vertical Text Interpreter for Natural Scene Images
title_full	Development of Vertical Text Interpreter for Natural Scene Images
title_fullStr	Development of Vertical Text Interpreter for Natural Scene Images
title_full_unstemmed	Development of Vertical Text Interpreter for Natural Scene Images
title_sort	development of vertical text interpreter for natural scene images
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/35cbd862fb13404c9f4c024f90235616
work_keys_str_mv	AT ongyiling developmentofverticaltextinterpreterfornaturalsceneimages AT laubeetheng developmentofverticaltextinterpreterfornaturalsceneimages AT almonchaiweiyen developmentofverticaltextinterpreterfornaturalsceneimages AT christophermccarthy developmentofverticaltextinterpreterfornaturalsceneimages
_version_	1718430307829415936

Development of Vertical Text Interpreter for Natural Scene Images

Ejemplares similares