{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T09:21:03Z","timestamp":1784884863076,"version":"3.55.0"},"reference-count":40,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2021,11,28]],"date-time":"2021-11-28T00:00:00Z","timestamp":1638057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Department of Yunnan Province","award":["202102AA310048"],"award-info":[{"award-number":["202102AA310048"]}]},{"name":"Science and Technology Department of Yunnan Province","award":["202102AA310045"],"award-info":[{"award-number":["202102AA310045"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s21237945","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T01:45:02Z","timestamp":1638323102000},"page":"7945","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Research on Classification Model of Panax notoginseng Taproots Based on Machine Vision Feature Fusion"],"prefix":"10.3390","volume":"21","author":[{"given":"Yinlong","family":"Zhu","sequence":"first","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fujie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"},{"name":"Engineering Research Center of Mechanization of Chinese Medicinal Materials of Yunnan Province, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixia","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"},{"name":"Engineering Research Center of Mechanization of Chinese Medicinal Materials of Yunnan Province, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Lin","sequence":"additional","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongxiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Shi","sequence":"additional","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Tao","sequence":"additional","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,28]]},"reference":[{"key":"ref_1","first-page":"41","article-title":"Planting, harvesting and processing status of Panax notoginseng","volume":"48","author":"Que","year":"2020","journal-title":"Jiangsu Agric. Sci."},{"key":"ref_2","first-page":"662","article-title":"Development trend analysis of Panax notoginseng","volume":"16","author":"Zhi","year":"2014","journal-title":"China Mod. Chin. Mater. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5526","DOI":"10.3390\/s21165526","article-title":"Artificial Intelligence Surgery: How Do We Get to Autonomous Actions in Surgery?","volume":"21","author":"Andrew","year":"2021","journal-title":"Sensors"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6073","DOI":"10.3390\/s21186073","article-title":"Functional Safety Networks and Protocols in the Industrial Internet of Things Era","volume":"21","author":"Giovanni","year":"2021","journal-title":"Sensors"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4801","DOI":"10.3390\/s21144801","article-title":"Weakly Supervised Crop Area Segmentation for an Autonomous Combine Harvester","volume":"21","author":"Taehyeong","year":"2021","journal-title":"Sensors"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5546","DOI":"10.3390\/s20195546","article-title":"Non-Destructive Assessment of Chicken Egg Fertility","volume":"20","author":"Adeyemi","year":"2020","journal-title":"Sensors"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, Y., Hong, Z., Cai, D., Huang, Y., Gong, L., and Liu, L. (2020). A SVM and SLIC Based Detection Method for Paddy Field Boundary Line. Sensors, 20.","DOI":"10.3390\/s20092610"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"107991","DOI":"10.1016\/j.measurement.2020.107991","article-title":"A calibration strategy for vision-guided robot assembly system of large cabin","volume":"163","author":"Jiang","year":"2020","journal-title":"Measurement"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1016\/j.camwa.2011.11.041","article-title":"Detection and classification of areca nuts with machine vision","volume":"64","author":"Huang","year":"2012","journal-title":"Comput. Math. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.compag.2017.03.016","article-title":"Vision-based pest detection based on SVM classification method","volume":"137","author":"Ebrahimi","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"105507","DOI":"10.1016\/j.compag.2020.105507","article-title":"Multiclass classification of dry beans using computer vision and machine learning techniques","volume":"174","author":"Murat","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_12","first-page":"129","article-title":"Deep learning architectures for semantic segmentation and automatic estimation of severity of foliar symptoms caused by diseases or pests","volume":"210","author":"Juliano","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106443","DOI":"10.1016\/j.compag.2021.106443","article-title":"Segmentation of abnormal leaves of hydroponic lettuce based on DeepLabV3+ for robotic sorting","volume":"190","author":"Wu","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_14","first-page":"178","article-title":"Automatic detecting and grading method of potatoes based on machine vision","volume":"28","author":"Zhou","year":"2012","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_15","first-page":"256","article-title":"Design and experiment of automatic sorting and grading system based on machine vision for white Agaricus bisporus","volume":"34","author":"Wang","year":"2018","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_16","first-page":"193","article-title":"Rapid recognition of potato late blight based on machine vision","volume":"36","author":"Dang","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_17","first-page":"182","article-title":"Improved RetinaNet-based automatic detection model for pests in rice canopy","volume":"36","author":"Yao","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_18","first-page":"177","article-title":"Carrot defect recognition and segmentation based on deep multi-branch model fusion network","volume":"37","author":"Xie","year":"2021","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_19","first-page":"682","article-title":"Quality classification method of Panax notoginseng taproot based on computer vision","volume":"42","author":"Yu","year":"2016","journal-title":"J. Hunan Agric. Univ."},{"key":"ref_20","unstructured":"(2018, July 31). GB\/T 19086-2008 Geographical Indication Product Wenshan Sanqi.2018-07-31. Available online: https:\/\/ishare.iask.sina.com.cn\/f\/17MhWQhZqMn.html."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.compag.2018.08.028","article-title":"Rice blast recognition based on principal component analysis and neural network","volume":"154","author":"Xiao","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_22","first-page":"287","article-title":"Grading for Tobacco Leaf Quality Based on Sparse Representation","volume":"44","author":"Xiang","year":"2013","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.compag.2018.09.017","article-title":"A computer vision approach based on endocarp features for the identification of olive cultivars","volume":"154","author":"Satorres","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_24","first-page":"279","article-title":"Grading Keemun black tea based on shape feature parameters of machine vision","volume":"34","author":"Song","year":"2018","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_25","first-page":"233","article-title":"Remote sensing monitoring of soil surface water content based on LM algorithm","volume":"50","author":"Xu","year":"2019","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1016\/j.compag.2017.06.023","article-title":"Machine vision based soybean quality evaluation","volume":"140","author":"Md","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"105865","DOI":"10.1016\/j.compag.2020.105865","article-title":"Mushroom spawn quality classification with machine learning","volume":"179","author":"Tongcham","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_28","first-page":"6456724","article-title":"A machine learning-based approach for the segmentation and classification of malignant cells in breast cytology images using gray level co-occurrence matrix (GLCM) and support vector machine (SVM)","volume":"23","author":"Sana","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.jfoodeng.2016.01.002","article-title":"Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine","volume":"179","author":"Zhang","year":"2016","journal-title":"J. Food Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"105590","DOI":"10.1016\/j.compag.2020.105590","article-title":"Weed density classification in rice crop using computer vision","volume":"175","author":"Taskeen","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_31","first-page":"262","article-title":"Nondestructive testing model for maize grain moisture content established by screening dielectric parameters and variables","volume":"35","author":"Song","year":"2019","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e14591","DOI":"10.1111\/jfpp.14591","article-title":"Classification detection of saccharin jujube based on hyperspectral imaging technology","volume":"44","author":"Zhang","year":"2020","journal-title":"J. Food Process. Preserv."},{"key":"ref_33","first-page":"172","article-title":"Estimation of Chlorophyll Content in Winter Wheat Based on Wavelet Transform and Fractional Differential","volume":"52","author":"Li","year":"2021","journal-title":"Trans. Chin. Soc. Agric."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.3233\/JIFS-210374","article-title":"Research on image classification method of strip steel surface defects based on improved Bat algorithm optimized BP neural network","volume":"41","author":"Yue","year":"2021","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"119956","DOI":"10.1016\/j.jns.2021.119956","article-title":"Classification of eye condition based on electroencephalogram signals using extreme learning machines algorithm (ELM)","volume":"429","author":"Fajar","year":"2021","journal-title":"J. Neurol. Sci."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.compag.2017.11.037","article-title":"A comparison of support vector machines, artificial neural network and classification tree for identifying soil texture classes in southwest China","volume":"144","author":"Wu","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"106482","DOI":"10.1016\/j.compag.2021.106482","article-title":"Feature detection method for hind leg segmentation of sheep carcass based on multi-scale dual attention U-Net","volume":"191","author":"Xie","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1007\/s12021-020-09492-6","article-title":"Deep LearningModel for the Automated Detection and Histopathological Prediction of Meningioma","volume":"3","author":"Zhang","year":"2021","journal-title":"Neuroinformatics"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"106373","DOI":"10.1016\/j.compag.2021.106373","article-title":"A cucumber leaf disease severity classification method based on the fusion of DeepLabV3+ and U-Net","volume":"189","author":"Wang","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_40","first-page":"96","article-title":"Research on Wheat Seed Classification and Recognition Based on Hyperspectral Imaging","volume":"39","author":"Zhang","year":"2019","journal-title":"J. Triticeae Crop."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7945\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:37:01Z","timestamp":1760168221000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,28]]},"references-count":40,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["s21237945"],"URL":"https:\/\/doi.org\/10.3390\/s21237945","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,28]]}}}