Recycling Waste Classification Using Vision Transformer on Portable Device

Recycling resources from waste can effectively alleviate the threat of global resource strain. Due to the wide variety of waste, relying on manual classification of waste and recycling recyclable resources would be costly and inefficient. In recent years, automatic recyclable waste classification ba...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kai Huang, Huan Lei, Zeyu Jiao, Zhenyu Zhong
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/016ce5d9f8814f79aa694e0d4f71ee4d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:016ce5d9f8814f79aa694e0d4f71ee4d
record_format dspace
spelling oai:doaj.org-article:016ce5d9f8814f79aa694e0d4f71ee4d2021-11-11T19:20:52ZRecycling Waste Classification Using Vision Transformer on Portable Device10.3390/su1321115722071-1050https://doaj.org/article/016ce5d9f8814f79aa694e0d4f71ee4d2021-10-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/21/11572https://doaj.org/toc/2071-1050Recycling resources from waste can effectively alleviate the threat of global resource strain. Due to the wide variety of waste, relying on manual classification of waste and recycling recyclable resources would be costly and inefficient. In recent years, automatic recyclable waste classification based on convolutional neural network (CNN) has become the mainstream method of waste recycling. However, due to the receptive field limitation of the CNN, the accuracy of classification has reached a bottleneck, which restricts the implementation of relevant methods and systems. In order to solve the above challenges, in this study, a deep neural network architecture only based on self-attention mechanism, named <i>Vision Transformer</i>, is proposed to improve the accuracy of automatic classification. Experimental results on TrashNet dataset show that the proposed method can achieve the highest accuracy of 96.98%, which is better than the existing CNN-based method. By deploying the well-trained model on the server and using a portable device to take pictures of waste in order to upload to the server, automatic waste classification can be expediently realized on the portable device, which broadens the scope of application of automatic waste classification and is of great significance with respect to resource conservation and recycling.Kai HuangHuan LeiZeyu JiaoZhenyu ZhongMDPI AGarticlewaste classificationautomatic recyclingdeep neural networkself-attentionportable deviceEnvironmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 11572, p 11572 (2021)
institution DOAJ
collection DOAJ
language EN
topic waste classification
automatic recycling
deep neural network
self-attention
portable device
Environmental effects of industries and plants
TD194-195
Renewable energy sources
TJ807-830
Environmental sciences
GE1-350
spellingShingle waste classification
automatic recycling
deep neural network
self-attention
portable device
Environmental effects of industries and plants
TD194-195
Renewable energy sources
TJ807-830
Environmental sciences
GE1-350
Kai Huang
Huan Lei
Zeyu Jiao
Zhenyu Zhong
Recycling Waste Classification Using Vision Transformer on Portable Device
description Recycling resources from waste can effectively alleviate the threat of global resource strain. Due to the wide variety of waste, relying on manual classification of waste and recycling recyclable resources would be costly and inefficient. In recent years, automatic recyclable waste classification based on convolutional neural network (CNN) has become the mainstream method of waste recycling. However, due to the receptive field limitation of the CNN, the accuracy of classification has reached a bottleneck, which restricts the implementation of relevant methods and systems. In order to solve the above challenges, in this study, a deep neural network architecture only based on self-attention mechanism, named <i>Vision Transformer</i>, is proposed to improve the accuracy of automatic classification. Experimental results on TrashNet dataset show that the proposed method can achieve the highest accuracy of 96.98%, which is better than the existing CNN-based method. By deploying the well-trained model on the server and using a portable device to take pictures of waste in order to upload to the server, automatic waste classification can be expediently realized on the portable device, which broadens the scope of application of automatic waste classification and is of great significance with respect to resource conservation and recycling.
format article
author Kai Huang
Huan Lei
Zeyu Jiao
Zhenyu Zhong
author_facet Kai Huang
Huan Lei
Zeyu Jiao
Zhenyu Zhong
author_sort Kai Huang
title Recycling Waste Classification Using Vision Transformer on Portable Device
title_short Recycling Waste Classification Using Vision Transformer on Portable Device
title_full Recycling Waste Classification Using Vision Transformer on Portable Device
title_fullStr Recycling Waste Classification Using Vision Transformer on Portable Device
title_full_unstemmed Recycling Waste Classification Using Vision Transformer on Portable Device
title_sort recycling waste classification using vision transformer on portable device
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/016ce5d9f8814f79aa694e0d4f71ee4d
work_keys_str_mv AT kaihuang recyclingwasteclassificationusingvisiontransformeronportabledevice
AT huanlei recyclingwasteclassificationusingvisiontransformeronportabledevice
AT zeyujiao recyclingwasteclassificationusingvisiontransformeronportabledevice
AT zhenyuzhong recyclingwasteclassificationusingvisiontransformeronportabledevice
_version_ 1718431507256705024