AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/IGARSS47720.2021.9553189 http://hdl.handle.net/11449/223593 |
Resumo: | Classifying targets in satellite images is a nontrivial task which requires dealing with a large number of undesirable elements such as clouds, building shadows and other unexpected objects. Among these, a commonly found element refers to artificially inserted post-processing objects like textual content, as the added text usually takes the form of watermarks, sensor specifications, street and place location names, etc. Manually selecting text segments is tedious, time-consuming, and requires the familiarity with image editing tools to precisely delineate these writing areas. Therefore, in this paper, a new automatic approach for detecting textual elements in satellite images is presented. Our approach combines cartoon-texture decomposition, thresholding-based rules, morphological operations, and connected component analysis into a fully automated and concise framework. Experiments on real satellite images and comparisons against well-established text detection methods demonstrate the high accuracy and low false-positive rate achieved by our approach when detecting textual content. |
id |
UNSP_eceb81d0bcd4b0968efa5dd5844f455c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/223593 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGESRemote sensing imagesText detectionClassifying targets in satellite images is a nontrivial task which requires dealing with a large number of undesirable elements such as clouds, building shadows and other unexpected objects. Among these, a commonly found element refers to artificially inserted post-processing objects like textual content, as the added text usually takes the form of watermarks, sensor specifications, street and place location names, etc. Manually selecting text segments is tedious, time-consuming, and requires the familiarity with image editing tools to precisely delineate these writing areas. Therefore, in this paper, a new automatic approach for detecting textual elements in satellite images is presented. Our approach combines cartoon-texture decomposition, thresholding-based rules, morphological operations, and connected component analysis into a fully automated and concise framework. Experiments on real satellite images and comparisons against well-established text detection methods demonstrate the high accuracy and low false-positive rate achieved by our approach when detecting textual content.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)São Paulo State University (UNESP) Dept. of Energy EngineeringFederal University of Itajubá (UNIFEI) Natural Resources InstituteSão Paulo State University (UNESP) Dept. of Environmental Engineering, S. J. dos CamposSão Paulo State University (UNESP) Dept. of Energy EngineeringSão Paulo State University (UNESP) Dept. of Environmental Engineering, S. J. dos CamposFAPESP: #2013/07375-0FAPESP: #2018/01033-3FAPESP: #2018/06756-3Universidade Estadual Paulista (UNESP)Natural Resources InstituteBasso, Dayara [UNESP]Colnago, Marilaine [UNESP]Azevedo, SamaraNegri, Rogério G. [UNESP]Casaca, Wallace [UNESP]2022-04-28T19:51:33Z2022-04-28T19:51:33Z2021-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject4204-4207http://dx.doi.org/10.1109/IGARSS47720.2021.9553189International Geoscience and Remote Sensing Symposium (IGARSS), v. 2021-July, p. 4204-4207.http://hdl.handle.net/11449/22359310.1109/IGARSS47720.2021.95531892-s2.0-85126017224Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengInternational Geoscience and Remote Sensing Symposium (IGARSS)info:eu-repo/semantics/openAccess2022-04-28T19:51:33Zoai:repositorio.unesp.br:11449/223593Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T21:11:51.192269Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES |
title |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES |
spellingShingle |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES Basso, Dayara [UNESP] Remote sensing images Text detection |
title_short |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES |
title_full |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES |
title_fullStr |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES |
title_full_unstemmed |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES |
title_sort |
AUTOMATICALLY DETECTING TEXTUAL CONTENT IN HIGH-RESOLUTION IMAGES |
author |
Basso, Dayara [UNESP] |
author_facet |
Basso, Dayara [UNESP] Colnago, Marilaine [UNESP] Azevedo, Samara Negri, Rogério G. [UNESP] Casaca, Wallace [UNESP] |
author_role |
author |
author2 |
Colnago, Marilaine [UNESP] Azevedo, Samara Negri, Rogério G. [UNESP] Casaca, Wallace [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Natural Resources Institute |
dc.contributor.author.fl_str_mv |
Basso, Dayara [UNESP] Colnago, Marilaine [UNESP] Azevedo, Samara Negri, Rogério G. [UNESP] Casaca, Wallace [UNESP] |
dc.subject.por.fl_str_mv |
Remote sensing images Text detection |
topic |
Remote sensing images Text detection |
description |
Classifying targets in satellite images is a nontrivial task which requires dealing with a large number of undesirable elements such as clouds, building shadows and other unexpected objects. Among these, a commonly found element refers to artificially inserted post-processing objects like textual content, as the added text usually takes the form of watermarks, sensor specifications, street and place location names, etc. Manually selecting text segments is tedious, time-consuming, and requires the familiarity with image editing tools to precisely delineate these writing areas. Therefore, in this paper, a new automatic approach for detecting textual elements in satellite images is presented. Our approach combines cartoon-texture decomposition, thresholding-based rules, morphological operations, and connected component analysis into a fully automated and concise framework. Experiments on real satellite images and comparisons against well-established text detection methods demonstrate the high accuracy and low false-positive rate achieved by our approach when detecting textual content. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-01 2022-04-28T19:51:33Z 2022-04-28T19:51:33Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/IGARSS47720.2021.9553189 International Geoscience and Remote Sensing Symposium (IGARSS), v. 2021-July, p. 4204-4207. http://hdl.handle.net/11449/223593 10.1109/IGARSS47720.2021.9553189 2-s2.0-85126017224 |
url |
http://dx.doi.org/10.1109/IGARSS47720.2021.9553189 http://hdl.handle.net/11449/223593 |
identifier_str_mv |
International Geoscience and Remote Sensing Symposium (IGARSS), v. 2021-July, p. 4204-4207. 10.1109/IGARSS47720.2021.9553189 2-s2.0-85126017224 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
International Geoscience and Remote Sensing Symposium (IGARSS) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
4204-4207 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808129297044471808 |