Intelligent garbage classification system based on improve MobileNetV3-Large

In response to the call for implementing national waste classification, this paper proposes an intelligent waste classification system based on the improved MobileNetV3-Large, which can raise the national awareness of waste classification through the combination of software and hardware. The softwar...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi Zhao, Hancheng Huang, Zhixiang Li, Huang Yiwang, Manjie Lu
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2022.2067127
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414185445752832
author Yi Zhao
Hancheng Huang
Zhixiang Li
Huang Yiwang
Manjie Lu
author_facet Yi Zhao
Hancheng Huang
Zhixiang Li
Huang Yiwang
Manjie Lu
author_sort Yi Zhao
collection DOAJ
description In response to the call for implementing national waste classification, this paper proposes an intelligent waste classification system based on the improved MobileNetV3-Large, which can raise the national awareness of waste classification through the combination of software and hardware. The software module is based on WeChat applet and offers functions for image recognition, text recognition, speech recognition, points-based quiz and so on. The hardware module is based on Raspberry Pi and covers image shooting, image recognition, automatic classification with automatic announcement and so on. The algorithm model applied to the image classification adopts a network model based on MobileNetV3-Large. This network model is enabled to classify garbage images through deep separable convolution, inverse residual structure, lightweight attention structure and the hard_ swish activation function. The text classification model adopts a network model based on LSTM, extracts text features through word embedding, enhancing the effect of garbage text classification. After testing, the system can leverage deep learning to realise intelligent garbage classification. The image recognition accuracy of the algorithm model was found to reach 81%, while the text recognition accuracy was as high as 97.61%.
format Article
id doaj-art-67e5c9c7539640cda4e0ee1d7af3d584
institution Kabale University
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-67e5c9c7539640cda4e0ee1d7af3d5842025-08-20T03:33:54ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013411299132110.1080/09540091.2022.20671272067127Intelligent garbage classification system based on improve MobileNetV3-LargeYi Zhao0Hancheng Huang1Zhixiang Li2Huang Yiwang3Manjie Lu4Guangdong Ocean UniversityGuangdong Ocean UniversityGuangdong Ocean UniversityTongren UniversityGuangdong Ocean UniversityIn response to the call for implementing national waste classification, this paper proposes an intelligent waste classification system based on the improved MobileNetV3-Large, which can raise the national awareness of waste classification through the combination of software and hardware. The software module is based on WeChat applet and offers functions for image recognition, text recognition, speech recognition, points-based quiz and so on. The hardware module is based on Raspberry Pi and covers image shooting, image recognition, automatic classification with automatic announcement and so on. The algorithm model applied to the image classification adopts a network model based on MobileNetV3-Large. This network model is enabled to classify garbage images through deep separable convolution, inverse residual structure, lightweight attention structure and the hard_ swish activation function. The text classification model adopts a network model based on LSTM, extracts text features through word embedding, enhancing the effect of garbage text classification. After testing, the system can leverage deep learning to realise intelligent garbage classification. The image recognition accuracy of the algorithm model was found to reach 81%, while the text recognition accuracy was as high as 97.61%.http://dx.doi.org/10.1080/09540091.2022.2067127deep learninggarbage classificationmobilenetv3-largelstmcombination of software and hardware
spellingShingle Yi Zhao
Hancheng Huang
Zhixiang Li
Huang Yiwang
Manjie Lu
Intelligent garbage classification system based on improve MobileNetV3-Large
Connection Science
deep learning
garbage classification
mobilenetv3-large
lstm
combination of software and hardware
title Intelligent garbage classification system based on improve MobileNetV3-Large
title_full Intelligent garbage classification system based on improve MobileNetV3-Large
title_fullStr Intelligent garbage classification system based on improve MobileNetV3-Large
title_full_unstemmed Intelligent garbage classification system based on improve MobileNetV3-Large
title_short Intelligent garbage classification system based on improve MobileNetV3-Large
title_sort intelligent garbage classification system based on improve mobilenetv3 large
topic deep learning
garbage classification
mobilenetv3-large
lstm
combination of software and hardware
url http://dx.doi.org/10.1080/09540091.2022.2067127
work_keys_str_mv AT yizhao intelligentgarbageclassificationsystembasedonimprovemobilenetv3large
AT hanchenghuang intelligentgarbageclassificationsystembasedonimprovemobilenetv3large
AT zhixiangli intelligentgarbageclassificationsystembasedonimprovemobilenetv3large
AT huangyiwang intelligentgarbageclassificationsystembasedonimprovemobilenetv3large
AT manjielu intelligentgarbageclassificationsystembasedonimprovemobilenetv3large