Cargando…

Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier

The Convolutional Neural Network (CNN) is one of the widely used deep learning models that offers the chance to boost farming productivity through autonomous inference of field conditions. In this paper, CNN is connected to a Support Vector Machine (SVM) to form a new model CNN-SVM; the CNN models c...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Yanjuan, He, Yuzhe, Wang, Yunliang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10458607/
https://www.ncbi.nlm.nih.gov/pubmed/37631689
http://dx.doi.org/10.3390/s23167153
_version_ 1785097206220455936
author Wu, Yanjuan
He, Yuzhe
Wang, Yunliang
author_facet Wu, Yanjuan
He, Yuzhe
Wang, Yunliang
author_sort Wu, Yanjuan
collection PubMed
description The Convolutional Neural Network (CNN) is one of the widely used deep learning models that offers the chance to boost farming productivity through autonomous inference of field conditions. In this paper, CNN is connected to a Support Vector Machine (SVM) to form a new model CNN-SVM; the CNN models chosen are ResNet-50 and VGG16 and the CNN-SVM models formed are ResNet-50-SVM and VGG16-SVM. The method consists of two parts: ResNet-50 and VGG16 for feature extraction and SVM for classification. This paper uses the public multi-class weeds dataset DeepWeeds for training and testing. The proposed ResNet-50-SVM and VGG16-SVM approaches achieved 97.6% and 95.9% recognition accuracies on the DeepWeeds dataset, respectively. The state-of-the-art networks (VGG16, ResNet-50, GoogLeNet, Densenet-121, and PSO-CNN) with the same dataset are accurate at 93.2%, 96.1%, 93.6%, 94.3%, and 96.9%, respectively. In comparison, the accuracy of the proposed methods has been improved by 1.5% and 2.7%, respectively. The proposed ResNet-50-SVM and the VGG16-SVM weed classification approaches are effective and can achieve high recognition accuracy.
format Online
Article
Text
id pubmed-10458607
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104586072023-08-27 Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier Wu, Yanjuan He, Yuzhe Wang, Yunliang Sensors (Basel) Article The Convolutional Neural Network (CNN) is one of the widely used deep learning models that offers the chance to boost farming productivity through autonomous inference of field conditions. In this paper, CNN is connected to a Support Vector Machine (SVM) to form a new model CNN-SVM; the CNN models chosen are ResNet-50 and VGG16 and the CNN-SVM models formed are ResNet-50-SVM and VGG16-SVM. The method consists of two parts: ResNet-50 and VGG16 for feature extraction and SVM for classification. This paper uses the public multi-class weeds dataset DeepWeeds for training and testing. The proposed ResNet-50-SVM and VGG16-SVM approaches achieved 97.6% and 95.9% recognition accuracies on the DeepWeeds dataset, respectively. The state-of-the-art networks (VGG16, ResNet-50, GoogLeNet, Densenet-121, and PSO-CNN) with the same dataset are accurate at 93.2%, 96.1%, 93.6%, 94.3%, and 96.9%, respectively. In comparison, the accuracy of the proposed methods has been improved by 1.5% and 2.7%, respectively. The proposed ResNet-50-SVM and the VGG16-SVM weed classification approaches are effective and can achieve high recognition accuracy. MDPI 2023-08-13 /pmc/articles/PMC10458607/ /pubmed/37631689 http://dx.doi.org/10.3390/s23167153 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wu, Yanjuan
He, Yuzhe
Wang, Yunliang
Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier
title Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier
title_full Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier
title_fullStr Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier
title_full_unstemmed Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier
title_short Multi-Class Weed Recognition Using Hybrid CNN-SVM Classifier
title_sort multi-class weed recognition using hybrid cnn-svm classifier
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10458607/
https://www.ncbi.nlm.nih.gov/pubmed/37631689
http://dx.doi.org/10.3390/s23167153
work_keys_str_mv AT wuyanjuan multiclassweedrecognitionusinghybridcnnsvmclassifier
AT heyuzhe multiclassweedrecognitionusinghybridcnnsvmclassifier
AT wangyunliang multiclassweedrecognitionusinghybridcnnsvmclassifier