Research on Classification of Medicinal Plant Leaves Based on Improved CNN

LIU Yi; SUN Yan-bin; ZHAI Feng-guo; LIANG Xin

doi:10.3969/j.issn.2096-6091.2023.13.002

您当前的位置：

首页 >

文章列表页 >

Research on Classification of Medicinal Plant Leaves Based on Improved CNN

RESEARCH PAPER | 更新时间：2025-03-26

- Research on Classification of Medicinal Plant Leaves Based on Improved CNN
- New Generation of Information Technology Vol. 6, Issue 13, Pages: 6-11(2023)
- 作者机构：
  
  1.牡丹江医学院，黑龙江牡丹江 157011
  2.牡丹江医学院附属红旗医院，黑龙江牡丹江 157011
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.2096-6091.2023.13.002
  CLC： TP391
- Accepted：2023-06-26，
  
  Published：15 July 2023
- 稿件说明：
移动端阅览
刘艺, 孙延斌, 翟凤国, 等. 基于改进CNN的药用植物叶片分类研究[J]. 新一代信息技术, 2023, 6(13): 06-11

LIU Yi, SUN Yan-bin, ZHAI Feng-guo, et al. Research on Classification of Medicinal Plant Leaves Based on Improved CNN[J]. New Generation of Information Technology, 2023, 6(13): 06-11
刘艺, 孙延斌, 翟凤国, 等. 基于改进CNN的药用植物叶片分类研究[J]. 新一代信息技术, 2023, 6(13): 06-11 DOI： 10.3969/j.issn.2096-6091.2023.13.002.

LIU Yi, SUN Yan-bin, ZHAI Feng-guo, et al. Research on Classification of Medicinal Plant Leaves Based on Improved CNN[J]. New Generation of Information Technology, 2023, 6(13): 06-11 DOI： 10.3969/j.issn.2096-6091.2023.13.002.

摘要

传统的植物叶片分类方法往往难以满足准确性和效率性的要求，本研究引入了VGG16模型作为改进的解决方案，旨在提高药用植物叶片分类的准确性和自动化程度。以基准CNN（Convolutional Neural Networks）模型在数据集上进行评估，用VGG16模型与基准CNN模型比较效果。VGG16模型在训练集上达到了97%的准确率，而验证集的准确率为94%。在相同的训练周期下，训练集和验证集的准确率分别为91.1%和93.4%。这表明VGG16模型在对药用植物叶片进行分类时具有更好的性能和泛化能力。VGG16模型在药用植物叶片分类任务中展现出了优异的性能，为高效精准的植物分类提供了有力的解决方案。未来的研究可以进一步改进和扩展深度学习模型，以应对更广泛和复杂的植物分类挑战。

Abstract

Traditional plant leaf classification methods often fail to meet the requirements of accuracy and efficiency. This study introduces the VGG16 model as an improved solution

aiming to improve the accuracy and automation of medicinal plant leaf classification.

and evaluates the benchmark CNN (Convolutional Neural Networks) model on the dataset and compare the effectiveness with the VGG16 model and the benchmark CNN model. The VGG16 model achieved an accuracy of 97% on the training set

while the accuracy of the validation set was 94%. Under the same training cycle

the accuracy of the training and validation sets is 91.1% and 93.4%

respectively. This indicates that the VGG16 model has better performance and generalization ability in classifying medicinal plant leaves. The VGG16 model exhibits excellent performance in the task of medicinal plant leaf classification

providing a powerful solution for efficient and accurate plant classification. Future research can further improve and expand deep learning models to address broader and complex plant classification challenges.

关键词

Keywords

references

CHEN L Y , LI S B , BAI Q A , et al . Review of image classification algorithms based on convolutional neural networks [J ] . Remote Sensing , 2021 , 13 ( 22 ): 4712 .

林正文 , 宋思瑜 , 范钧玮 , 等 . 改进YOLOv5的光伏组件热斑及遮挡小目标检测 [J/OL ] . 计算机工程与应用 , 2023 : 1 - 13 . ( 2023-05-17 )[ 2023-09-04 ] . http://kns.cnki.net/kcms/detail/11.2127.TP.20230517.1324.003.html http://kns.cnki.net/kcms/detail/11.2127.TP.20230517.1324.003.html .

张世龙 . 基于深度学习的阿尔巴斯绒山羊面部识别研究 [D ] . 呼和浩特 : 内蒙古大学 , 2022 .

史雨林 . 基于点云深度学习的颅颌面畸形手术规划方法及初步临床应用 [D ] . 西安 : 中国人民解放军空军军医大学 , 2022 .

BARUAH M , BANERJEE B , NAGAR A K , et al . AttentionMNIST: A mouse-click attention tracking dataset for handwritten numeral and alphabet recognition [J ] . Scientific Reports , 2023 , 13 : 3305 .

尹显明 , 棘玉 , 张日清 , 等 . 深度学习在基于叶片的油茶品种识别中的研究 [J ] . 南京林业大学学报(自然科学版) , 2023 , 47 ( 3 ): 29 - 36 .

HASAN A S M M , SOHEL F , DIEPEVEEN D , et al . A survey of deep learning techniques for weed detection from images [J ] . Computers and Electronics in Agriculture , 2021 , 184 : 106067 .

余得正 . 基于改进深度残差网络与注意力机制的植物叶片图像识别研究 [D ] . 广州 : 广东技术师范大学 , 2022 .

王丽君 , 淮永建 , 彭月橙 . 基于叶片图像多特征融合的观叶植物种类识别 [J ] . 北京林业大学学报 , 2015 , 37 ( 1 ): 55 - 61 .

吴冲 . 基于深度学习的中药材鉴别方法研究 [D ] . 成都 : 四川大学 , 2021 .

SEELAND M , RZANNY M , BOHO D , et al . Image-based classification of plant genus and family for trained and untrained plant species [J ] . BMC Bioinformatics , 2019 , 20 ( 1 ): 1 - 13 .

KRISHNAMOORTHY N , NARASIMHA PRASAD L V , PAVAN KUMAR C S , et al . Rice leaf diseases prediction using deep neural networks with transfer learning [J ] . Environmental Research , 2021 , 198 : 111275 .

TOO E C , LI Y J , NJUKI S , et al . A comparative study of fine-tuning deep learning models for plant disease identification [J ] . Computers and Electronics in Agriculture , 2019 , 161 : 272 - 279 .

张林朋 , 杨红云 , 钱政 , 等 . 基于改进的VGG16网络和迁移学习的水稻氮素营养诊断 [J ] . 中国农业大学学报 , 2023 , 28 ( 6 ): 219 - 229 .

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [EB/OL ] . ( 2014 )[ 2023-04-25 ] . DOI: 10.48550/arXiv.1409.1556 http://dx.doi.org/10.48550/arXiv.1409.1556 .

Views

162

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Predictive Study of Breast Cancer Pathological Images Based on DenseNet201

Application and Prospect of Deep Learning Technology in Medical Image Analysis

Study on the Recognition of Maize Leaf Disease Based on Deep Learning with Small Sample Size

Study of the Joint Framework for Real-World Super-Resolution-Semantic Segmentation

Related Author

ZHAI Feng-guo

LIANG Xin

GAO Ming-ze

HAN Yang

CHEN Guang-xin

GUO Jin-xing

SUN Yue

MIAO Zhuang

Related Institution

Mudanjiang Medical College Affiliated Hongqi Hospital

Hongqi Hospital Affiliated with Mudanjiang Medical University

Basic Medical College of Mudanjiang Medical University

Medical Imaging College of Mudanjiang Medical University

Chongqing Communication Design Institute Co., Ltd

⁰