A robust approach for industrial small-object detection using an improved faster regional convolutional neural network

Abstract With the increasing pace in the industrial sector, the need for a smart environment is also increasing and the production of industrial products in terms of quality always matters. There is a strong burden on the industrial environment to continue to reduce impulsive downtime, concert depri...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Faisal Saeed, Muhammad Jamal Ahmed, Malik Junaid Gul, Kim Jeong Hong, Anand Paul, Muthu Subash Kavitha
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/cdad2c92ae74400e8c8aaf170209e172
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cdad2c92ae74400e8c8aaf170209e172
record_format	dspace
spelling	oai:doaj.org-article:cdad2c92ae74400e8c8aaf170209e1722021-12-05T12:16:20ZA robust approach for industrial small-object detection using an improved faster regional convolutional neural network10.1038/s41598-021-02805-y2045-2322https://doaj.org/article/cdad2c92ae74400e8c8aaf170209e1722021-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-02805-yhttps://doaj.org/toc/2045-2322Abstract With the increasing pace in the industrial sector, the need for a smart environment is also increasing and the production of industrial products in terms of quality always matters. There is a strong burden on the industrial environment to continue to reduce impulsive downtime, concert deprivation, and safety risks, which needs an efficient solution to detect and improve potential obligations as soon as possible. The systems working in industrial environments for generating industrial products are very fast and generate products rapidly, sometimes leading to faulty products. Therefore, this problem needs to be solved efficiently. Considering this problem in terms of faulty small-object detection, this study proposed an improved faster regional convolutional neural network-based model to detect the faults in the product images. We introduced a novel data-augmentation method along with a bi-cubic interpolation-based feature amplification method. A center loss is also introduced in the loss function to decrease the inter-class similarity issue. The experimental results show that the proposed improved model achieved better classification accuracy for detecting our small faulty objects. The proposed model performs better than the state-of-the-art methods.Faisal SaeedMuhammad Jamal AhmedMalik Junaid GulKim Jeong HongAnand PaulMuthu Subash KavithaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Faisal Saeed Muhammad Jamal Ahmed Malik Junaid Gul Kim Jeong Hong Anand Paul Muthu Subash Kavitha A robust approach for industrial small-object detection using an improved faster regional convolutional neural network
description	Abstract With the increasing pace in the industrial sector, the need for a smart environment is also increasing and the production of industrial products in terms of quality always matters. There is a strong burden on the industrial environment to continue to reduce impulsive downtime, concert deprivation, and safety risks, which needs an efficient solution to detect and improve potential obligations as soon as possible. The systems working in industrial environments for generating industrial products are very fast and generate products rapidly, sometimes leading to faulty products. Therefore, this problem needs to be solved efficiently. Considering this problem in terms of faulty small-object detection, this study proposed an improved faster regional convolutional neural network-based model to detect the faults in the product images. We introduced a novel data-augmentation method along with a bi-cubic interpolation-based feature amplification method. A center loss is also introduced in the loss function to decrease the inter-class similarity issue. The experimental results show that the proposed improved model achieved better classification accuracy for detecting our small faulty objects. The proposed model performs better than the state-of-the-art methods.
format	article
author	Faisal Saeed Muhammad Jamal Ahmed Malik Junaid Gul Kim Jeong Hong Anand Paul Muthu Subash Kavitha
author_facet	Faisal Saeed Muhammad Jamal Ahmed Malik Junaid Gul Kim Jeong Hong Anand Paul Muthu Subash Kavitha
author_sort	Faisal Saeed
title	A robust approach for industrial small-object detection using an improved faster regional convolutional neural network
title_short	A robust approach for industrial small-object detection using an improved faster regional convolutional neural network
title_full	A robust approach for industrial small-object detection using an improved faster regional convolutional neural network
title_fullStr	A robust approach for industrial small-object detection using an improved faster regional convolutional neural network
title_full_unstemmed	A robust approach for industrial small-object detection using an improved faster regional convolutional neural network
title_sort	robust approach for industrial small-object detection using an improved faster regional convolutional neural network
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/cdad2c92ae74400e8c8aaf170209e172
work_keys_str_mv	AT faisalsaeed arobustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT muhammadjamalahmed arobustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT malikjunaidgul arobustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT kimjeonghong arobustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT anandpaul arobustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT muthusubashkavitha arobustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT faisalsaeed robustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT muhammadjamalahmed robustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT malikjunaidgul robustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT kimjeonghong robustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT anandpaul robustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork AT muthusubashkavitha robustapproachforindustrialsmallobjectdetectionusinganimprovedfasterregionalconvolutionalneuralnetwork
_version_	1718372104043233280

A robust approach for industrial small-object detection using an improved faster regional convolutional neural network

Ejemplares similares