Cargando…

Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion

The existing classification methods for Panax notoginseng taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for Panax notoginseng taproots. The images of Panax notoginseng taproots collected in th...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhu, Yinlong, Zhang, Fujie, Li, Lixia, Lin, Yuhao, Zhang, Zhongxiong, Shi, Lei, Tao, Huan, Qin, Tao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8659782/
https://www.ncbi.nlm.nih.gov/pubmed/34883948
http://dx.doi.org/10.3390/s21237945
_version_ 1784613046288646144
author Zhu, Yinlong
Zhang, Fujie
Li, Lixia
Lin, Yuhao
Zhang, Zhongxiong
Shi, Lei
Tao, Huan
Qin, Tao
author_facet Zhu, Yinlong
Zhang, Fujie
Li, Lixia
Lin, Yuhao
Zhang, Zhongxiong
Shi, Lei
Tao, Huan
Qin, Tao
author_sort Zhu, Yinlong
collection PubMed
description The existing classification methods for Panax notoginseng taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for Panax notoginseng taproots. The images of Panax notoginseng taproots collected in the experiment are preprocessed by Gaussian filtering, binarization, and morphological methods. Then, a total of 40 features are extracted, including size and shape features, HSV and RGB color features, and texture features. Through BP neural network, extreme learning machine (ELM), and support vector machine (SVM) models, the importance of color, texture, and fusion features for the classification of the main roots of Panax notoginseng is verified. Among the three models, the SVM model performs the best, achieving an accuracy of 92.037% on the prediction set. Next, iterative retaining information variables (IRIVs), variable iterative space shrinkage approach (VISSA), and stepwise regression analysis (SRA) are used to reduce the dimension of all the features. Finally, a traditional machine learning SVM model based on feature selection and a deep learning model based on semantic segmentation are established. With the model size of only 125 kb and the training time of 3.4 s, the IRIV-SVM model achieves an accuracy of 95.370% on the test set, so IRIV-SVM is selected as the main root classification model for Panax notoginseng. After being optimized by the gray wolf optimizer, the IRIV-GWO-SVM model achieves the highest classification accuracy of 98.704% on the test set. The study results of this paper provide a basis for developing online classification methods of Panax notoginseng with different grades in actual production.
format Online
Article
Text
id pubmed-8659782
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86597822021-12-10 Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion Zhu, Yinlong Zhang, Fujie Li, Lixia Lin, Yuhao Zhang, Zhongxiong Shi, Lei Tao, Huan Qin, Tao Sensors (Basel) Article The existing classification methods for Panax notoginseng taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for Panax notoginseng taproots. The images of Panax notoginseng taproots collected in the experiment are preprocessed by Gaussian filtering, binarization, and morphological methods. Then, a total of 40 features are extracted, including size and shape features, HSV and RGB color features, and texture features. Through BP neural network, extreme learning machine (ELM), and support vector machine (SVM) models, the importance of color, texture, and fusion features for the classification of the main roots of Panax notoginseng is verified. Among the three models, the SVM model performs the best, achieving an accuracy of 92.037% on the prediction set. Next, iterative retaining information variables (IRIVs), variable iterative space shrinkage approach (VISSA), and stepwise regression analysis (SRA) are used to reduce the dimension of all the features. Finally, a traditional machine learning SVM model based on feature selection and a deep learning model based on semantic segmentation are established. With the model size of only 125 kb and the training time of 3.4 s, the IRIV-SVM model achieves an accuracy of 95.370% on the test set, so IRIV-SVM is selected as the main root classification model for Panax notoginseng. After being optimized by the gray wolf optimizer, the IRIV-GWO-SVM model achieves the highest classification accuracy of 98.704% on the test set. The study results of this paper provide a basis for developing online classification methods of Panax notoginseng with different grades in actual production. MDPI 2021-11-28 /pmc/articles/PMC8659782/ /pubmed/34883948 http://dx.doi.org/10.3390/s21237945 Text en © 2021 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
Zhu, Yinlong
Zhang, Fujie
Li, Lixia
Lin, Yuhao
Zhang, Zhongxiong
Shi, Lei
Tao, Huan
Qin, Tao
Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion
title Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion
title_full Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion
title_fullStr Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion
title_full_unstemmed Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion
title_short Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion
title_sort research on classification model of panax notoginseng taproots based on machine vision feature fusion
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8659782/
https://www.ncbi.nlm.nih.gov/pubmed/34883948
http://dx.doi.org/10.3390/s21237945
work_keys_str_mv AT zhuyinlong researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion
AT zhangfujie researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion
AT lilixia researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion
AT linyuhao researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion
AT zhangzhongxiong researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion
AT shilei researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion
AT taohuan researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion
AT qintao researchonclassificationmodelofpanaxnotoginsengtaprootsbasedonmachinevisionfeaturefusion