A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Revista de Engenharia e Pesquisa Aplicada |
Texto Completo: | http://revistas.poli.br/index.php/repa/article/view/1358 |
Resumo: | In the construction, installation, and maintenance of Radio station, employees need to create reports with information and real photos to prove that each provided service was accomplished. The creation of this report is generally slow, costly, and unpredictable. This occurs mainly due to the manual process involved in the incorrect acquiring of the images. On the other hand, computer vision techniques can significantly decrease the time and cost of this activity, avoiding illegible or incorrectly captures of the station board images. Thus, this work aims to propose a mobile tool to perform a validation of these images of the station board, using computer vision and artificial intelligence techniques. Thus, a tool was developed using the Python language, the pre-trained network EAST, and the Tesseract and Kivy libraries. We validated the approach in real-world cases, and the method was able to extract the default key text correctly. However, in non-board images, the proposal still needs some tuning to extract the key-text correctly. The primary goals of the research were accomplished since the tool was able to perform a validation of the board image. We intend to include new strategies to improve text recognition capabilities. |
id |
UFPE-2_d6c3c3bf30d69098b5e4038479cd4de9 |
---|---|
oai_identifier_str |
oai:ojs.poli.br:article/1358 |
network_acronym_str |
UFPE-2 |
network_name_str |
Revista de Engenharia e Pesquisa Aplicada |
repository_id_str |
|
spelling |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural ScenesFerramenta para Validação de Imagens Em Estações de Rádio Base Usando Reconhecimento de Texto Em Cenas NaturaisIn the construction, installation, and maintenance of Radio station, employees need to create reports with information and real photos to prove that each provided service was accomplished. The creation of this report is generally slow, costly, and unpredictable. This occurs mainly due to the manual process involved in the incorrect acquiring of the images. On the other hand, computer vision techniques can significantly decrease the time and cost of this activity, avoiding illegible or incorrectly captures of the station board images. Thus, this work aims to propose a mobile tool to perform a validation of these images of the station board, using computer vision and artificial intelligence techniques. Thus, a tool was developed using the Python language, the pre-trained network EAST, and the Tesseract and Kivy libraries. We validated the approach in real-world cases, and the method was able to extract the default key text correctly. However, in non-board images, the proposal still needs some tuning to extract the key-text correctly. The primary goals of the research were accomplished since the tool was able to perform a validation of the board image. We intend to include new strategies to improve text recognition capabilities.Atualmente, empresas do segmento de construção, instalação e manutenção de estações de rádio necessitam criar relatórios com informações e fotos reais para comprovar cada serviço prestado. A criação desse relatório pode ser lento, custoso e imprevisível devido ao processo manual envolvido na captura incorreta das imagens. Por outro lado, técnicas de visão computacional podem diminuir significantemente o tempo e o custo dessa atividade, evitando capturas ilegíveis ou com informações incorretas nas imagens placa da estação. Dessa forma, esse trabalho tem como objetivo propor uma ferramenta móvel para realizar uma validação dessas imagens da placa da estação, utilizando técnicas de visão computacional. Com isso, foi desenvolvida uma ferramenta utilizando a linguagem Python, a rede pré-treinada EAST e as bibliotecas Tesseract e Kivy. Como resultado para as imagens da placa esse método conseguiu extrair corretamente o texto chave predeterminado. Entretanto, para as imagens diferentes da placa ainda necessita de alguns ajustes para extrair o texto chave. O objetivo desse trabalho foi atingido, pois, a ferramenta foi capaz de validar a imagem da placa. Contudo, novas estratégias serão analisadas para melhorar o reconhecimento do texto.Escola Politécnica de Pernambuco2020-05-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionAvaliado pelos paresapplication/pdftext/htmlhttp://revistas.poli.br/index.php/repa/article/view/135810.25286/repa.v5i2.1358Journal of Engineering and Applied Research; Vol 5 No 2 (2020): Edição Especial em Inteligência Artificial; 91-97Revista de Engenharia e Pesquisa Aplicada; v. 5 n. 2 (2020): Edição Especial em Inteligência Artificial; 91-972525-425110.25286/repa.v5i2reponame:Revista de Engenharia e Pesquisa Aplicadainstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEporhttp://revistas.poli.br/index.php/repa/article/view/1358/626http://revistas.poli.br/index.php/repa/article/view/1358/627Copyright (c) 2020 José Antônio Pedro dos Santos, Carmelo Bastos-Filho, DRº, Victor Mendonca de Azevedohttp://creativecommons.org/licenses/by-nc/4.0info:eu-repo/semantics/openAccessdos Santos, José Antônio PedroBastos-Filho, CarmeloAzevedo, Victor Mendonca de2021-07-13T08:40:56Zoai:ojs.poli.br:article/1358Revistahttp://revistas.poli.br/index.php/repaONGhttp://revistas.poli.br/index.php/repa/oai||repa@poli.br2525-42512525-4251opendoar:2021-07-13T08:40:56Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE)false |
dc.title.none.fl_str_mv |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes Ferramenta para Validação de Imagens Em Estações de Rádio Base Usando Reconhecimento de Texto Em Cenas Naturais |
title |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes |
spellingShingle |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes dos Santos, José Antônio Pedro |
title_short |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes |
title_full |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes |
title_fullStr |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes |
title_full_unstemmed |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes |
title_sort |
A Tool for Images Validation in Cell Sites using Text Recognition in Natural Scenes |
author |
dos Santos, José Antônio Pedro |
author_facet |
dos Santos, José Antônio Pedro Bastos-Filho, Carmelo Azevedo, Victor Mendonca de |
author_role |
author |
author2 |
Bastos-Filho, Carmelo Azevedo, Victor Mendonca de |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
dos Santos, José Antônio Pedro Bastos-Filho, Carmelo Azevedo, Victor Mendonca de |
description |
In the construction, installation, and maintenance of Radio station, employees need to create reports with information and real photos to prove that each provided service was accomplished. The creation of this report is generally slow, costly, and unpredictable. This occurs mainly due to the manual process involved in the incorrect acquiring of the images. On the other hand, computer vision techniques can significantly decrease the time and cost of this activity, avoiding illegible or incorrectly captures of the station board images. Thus, this work aims to propose a mobile tool to perform a validation of these images of the station board, using computer vision and artificial intelligence techniques. Thus, a tool was developed using the Python language, the pre-trained network EAST, and the Tesseract and Kivy libraries. We validated the approach in real-world cases, and the method was able to extract the default key text correctly. However, in non-board images, the proposal still needs some tuning to extract the key-text correctly. The primary goals of the research were accomplished since the tool was able to perform a validation of the board image. We intend to include new strategies to improve text recognition capabilities. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-05-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Avaliado pelos pares |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://revistas.poli.br/index.php/repa/article/view/1358 10.25286/repa.v5i2.1358 |
url |
http://revistas.poli.br/index.php/repa/article/view/1358 |
identifier_str_mv |
10.25286/repa.v5i2.1358 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
http://revistas.poli.br/index.php/repa/article/view/1358/626 http://revistas.poli.br/index.php/repa/article/view/1358/627 |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf text/html |
dc.publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
dc.source.none.fl_str_mv |
Journal of Engineering and Applied Research; Vol 5 No 2 (2020): Edição Especial em Inteligência Artificial; 91-97 Revista de Engenharia e Pesquisa Aplicada; v. 5 n. 2 (2020): Edição Especial em Inteligência Artificial; 91-97 2525-4251 10.25286/repa.v5i2 reponame:Revista de Engenharia e Pesquisa Aplicada instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Revista de Engenharia e Pesquisa Aplicada |
collection |
Revista de Engenharia e Pesquisa Aplicada |
repository.name.fl_str_mv |
Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
||repa@poli.br |
_version_ |
1798035999859671040 |