Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature Fusion
The existing classification methods for <i>Panax notoginseng</i> taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for <i>Panax notoginseng</i> taproots. The images of <...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/7945 |
| _version_ | 1797507194346799104 |
|---|---|
| author | Yinlong Zhu Fujie Zhang Lixia Li Yuhao Lin Zhongxiong Zhang Lei Shi Huan Tao Tao Qin |
| author_facet | Yinlong Zhu Fujie Zhang Lixia Li Yuhao Lin Zhongxiong Zhang Lei Shi Huan Tao Tao Qin |
| author_sort | Yinlong Zhu |
| collection | DOAJ |
| description | The existing classification methods for <i>Panax notoginseng</i> taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for <i>Panax notoginseng</i> taproots. The images of <i>Panax notoginseng</i> 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 <i>Panax notoginseng</i> 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 <i>Panax notoginseng</i>. 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 <i>Panax notoginseng</i> with different grades in actual production. |
| first_indexed | 2024-03-10T04:45:09Z |
| format | Article |
| id | doaj.art-1fc3efa9619f414bb7a04d01ffa5463c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:45:09Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1fc3efa9619f414bb7a04d01ffa5463c2023-11-23T03:01:35ZengMDPI AGSensors1424-82202021-11-012123794510.3390/s21237945Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature FusionYinlong Zhu0Fujie Zhang1Lixia Li2Yuhao Lin3Zhongxiong Zhang4Lei Shi5Huan Tao6Tao Qin7Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaFaculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaThe existing classification methods for <i>Panax notoginseng</i> taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for <i>Panax notoginseng</i> taproots. The images of <i>Panax notoginseng</i> 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 <i>Panax notoginseng</i> 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 <i>Panax notoginseng</i>. 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 <i>Panax notoginseng</i> with different grades in actual production.https://www.mdpi.com/1424-8220/21/23/7945machine visionmachine learning<i>Panax notoginseng</i> taprootfeature fusionimage processinghierarchical model |
| spellingShingle | Yinlong Zhu Fujie Zhang Lixia Li Yuhao Lin Zhongxiong Zhang Lei Shi Huan Tao Tao Qin Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature Fusion Sensors machine vision machine learning <i>Panax notoginseng</i> taproot feature fusion image processing hierarchical model |
| title | Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature Fusion |
| title_full | Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature Fusion |
| title_fullStr | Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature Fusion |
| title_full_unstemmed | Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature Fusion |
| title_short | Research on Classification Model of <i>Panax notoginseng</i> Taproots Based on Machine Vision Feature Fusion |
| title_sort | research on classification model of i panax notoginseng i taproots based on machine vision feature fusion |
| topic | machine vision machine learning <i>Panax notoginseng</i> taproot feature fusion image processing hierarchical model |
| url | https://www.mdpi.com/1424-8220/21/23/7945 |
| work_keys_str_mv | AT yinlongzhu researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion AT fujiezhang researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion AT lixiali researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion AT yuhaolin researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion AT zhongxiongzhang researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion AT leishi researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion AT huantao researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion AT taoqin researchonclassificationmodelofipanaxnotoginsengitaprootsbasedonmachinevisionfeaturefusion |