智能化农业装备学报（中英文）

基于改进VGG-16的烟叶成熟度识别

预览PDF | 下载PDF

肖孟宇 ¹ , 马云明 ¹ , 肖亦雄 ¹ , 陆峰 ² , 唐忠海 ³ , 李跑 ³^,⁴ , 范伟 ³^,^*^,^* , 肖航 ⁵

智能化农业装备学报（中英文） | 2025,6(2): 79-87

收起

智能化农业装备学报（中英文） | 2025 , 6 (2) : 79 -87

基于改进VGG-16的烟叶成熟度识别

全屏

肖孟宇¹, 马云明¹, 肖亦雄¹, 陆峰², 唐忠海³, 李跑³^,⁴, 范伟³^,^*^,^*, 肖航⁵

作者信息

^1.湖南省烟草公司衡阳市公司，湖南衡阳，421000

^2.湖北中烟工业有限责任公司，湖北武汉，430040

^3.湖南农业大学食品科学技术学院，湖南长沙，410128

^4.食品科学与生物技术湖南省重点实验室，湖南长沙，410128

^5.麻省大学阿莫斯特分校食品科学系，美国马萨诸塞州阿莫斯特，01003

通讯作者:

^* 范伟，男，1983年生，河北邢台人，博士，讲师；研究方向为农产品加工智能检测。E-mail：weifan@hunau.edu.cn

作者简介:

肖孟宇，男，1989年生，湖南邵阳人，助理农艺师；研究方向为烟草栽培。E-mail：253875445@qq.com

Fresh tobacco maturity recognition based on the improved VGG-16 model

Mengyu XIAO¹, Yunming MA¹, Yixiong XIAO¹, Feng LU², Zhonghai TANG³, Pao LI³^,⁴, Wei FAN³, Hang XIAO⁵

Affiliations

^1.Hengyang Branch of Hunan Provincial Tobacco Company, Hengyang 421000, China

^2.Hubei Tobacco Industry Co., Ltd., Wuhan 430040, China

^3.College of Food Science and Technology, Hunan Agricultural University, Changsha 410128, China

^4.Hunan Province Key Laboratory of Food Science and Biotechnology, Changsha 410128, China

^5.Department of Food Science, University of Massachusetts-Amherst, Amherst, Massachusetts 01003, USA

Corresponding Author:

^* FAN Wei, E-mail: weifan@hunau.edu.cn

XIAO Mengyu, E-mail: 253875445@qq.com

出版时间: 2025-05-15 doi: 10.12398/j.issn.2096-7217.2025.02.007

文章导航

摘要

收起

为提高采收时不同部位烟叶成熟度识别准确率，本研究系统收集上、中、下部3个部位烟叶的欠熟、适熟、过熟图像，提出一种基于深度学习的改进VGG-16的烟叶成熟度识别方法。该方法使用迁移学习预训练VGG-16模型作为基础模型，并对其进行微调、卷积层特征融合，以提升模型在烟叶成熟度识别任务上的性能，冻结卷积层及后续层的微调、添加BN层和使用Adam优化器，进一步提高了训练效率、避免过拟合现象产生并增强模型的稳健性和精确度。试验结果表明，改进后的VGG-16模型在烟叶成熟度识别任务中具有高准确度的优势，其测试集识别准确率达到99.7%，优于经典机器学习BP神经网络、支持向量机、原始VGG-16和VGG-19、AlexNet、ResNet50等方法结果。其参数量为14 721 353、模型大小为58.9 M、单张图像识别时间为0.024 9 s，表现出计算和存储资源需求低，识别速度快的高效优势。进一步通过Score-CAM算法对不同成熟度烟叶图像识别结果进行可视化分析，揭示了烟叶主脉中部区域为不同成熟度烟叶核心差异区域，为识别模型提供关键信息，进而可为明确不同部位烟叶成熟过程中化学物质转化规律提供信息。本研究提出的改进VGG-16深度学习模型在不同部位烟叶成熟度识别上具有高准确率和高效率的优势，有望为烟草采收生产提供精准有效的决策支持。未来可进一步探讨不同的特征融合策略和网络结构，以提高不同产地及不同年份间烟叶成熟度识别的泛化能力和稳健性。

关键词

烟叶成熟度 / 深度学习 / 改进VGG-16 / 迁移学习 / 图像分类

Abstract

收起

To improve the accuracy of identifying the maturity of tobacco leaves at different harvesting stages, this study systematically collected images of under-ripe, ripe, and over-ripe tobacco leaves from the upper, middle, and lower parts of the plant. We proposed an improved VGG-16-based deep learning method for tobacco leaf maturity recognition. This method leverages a pre-trained VGG-16 model as its foundation, incorporating transfer learning, fine-tuning, and convolutional layer feature fusion to enhance the model's performance in tobacco leaf maturity recognition tasks. Freezing the convolutional and subsequent layers, adding BN layers, and using the Adam optimizer further improved training efficiency, avoided over fitting, and enhanced the model's robustness and accuracy. Experimental results showed that the improved VGG-16 model had a high accuracy advantage in tobacco leaf maturity recognition tasks, with a test set accuracy of 99.7%, surpassing classical machine learning methods such as BP neural networks, support vector machines, original VGG-16 and VGG-19, AlexNet, and ResNet50. The model comprised 14 721 353 parameters, a model size of 58.9 M, and a single image recognition time of 0.024 9 seconds, demonstrating the advantages of low computational and storage resource requirements and rapid recognition speed. Further visual analysis of the recognition results of tobacco leaf images with different maturities using the Score-CAM algorithm revealed that the central region of the main vein of tobacco leaves served as a primary differentiating feature for tobacco leaves with different maturities across different stalk positions, providing key information for the recognition model, there by clarifying the chemical substance transformation patterns occurring during the maturity process of tobacco leaves from distinct plant sections. The improved VGG-16 deep learning model proposed in this study exhibits high accuracy and efficiency in identifying the maturity of tobacco leaves at different harvesting stages. It is poised to provide precise and effective decision support for tobacco harvesting and production. Future research will focus on exploring alternative feature fusion strategies and network structures to further improve the generalization ability and robustness of tobacco leaf maturity recognition across different production areas and years.

Key words

tobacco maturity / deep learning / improved VGG-16 / transfer learning / image classification

引用本文

肖孟宇, 马云明, 肖亦雄, 陆峰, 唐忠海, 李跑, 范伟, 肖航. 基于改进VGG-16的烟叶成熟度识别. 智能化农业装备学报（中英文）, 2025 , 6 (2) : 79 -87 . DOI: 10.12398/j.issn.2096-7217.2025.02.007

Mengyu XIAO, Yunming MA, Yixiong XIAO, Feng LU, Zhonghai TANG, Pao LI, Wei FAN, Hang XIAO. Fresh tobacco maturity recognition based on the improved VGG-16 model[J]. Journal of Intelligent Agricultural Mechanization, 2025 , 6 (2) : 79 -87 . DOI: 10.12398/j.issn.2096-7217.2025.02.007

基金

收起

国家自然科学基金项目(32360579)
湖南省教育厅重点项目(20A230)
湖南省烟草公司衡阳市公司科技项目(2021430481240017)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

许自成，赵瑞蕊，王龙宪，等．烟叶成熟度的研究进展[J]．东北农业大学学报，2014，45（1）：123-128.

XU Zicheng, ZHAO Ruirui, WANG Longxian, et al. Research advance of maturity of flue-cured tobacco leaves [J]. Journal of Northeast Agricultural University, 2014, 45(1): 123-128.

[2]

杨树勋．准确判断烟叶采收成熟度初探[J]．中国烟草科学，2003（4）：34-36.

YANG Shuxun. Preliminary study on accurately judging the harvesting maturity of tobacco leaves [J]. Chinese Tobacco Science, 2003(4): 34-36.

[3]

崔国民，罗以贵．云南烤烟烘烤工艺的多样性分析[J]．云南农业大学学报，2000（15）：121-125.

CUI Guomin, LUO Yigui. A variety of researches into curing process of Yunnan tobacco [J]. Journal of Yunnan Agricultural University, 2000(15): 121-125.

[4]

YAO P F, ZHAO H X, LUO X P, et al. Fagopyrum tataricum FtWD40 functions as a positive regulator of anthocyanin biosynthesis in transgenic tobacco [J]. Journal of Plant Growth Regulation, 2017, 36: 755-765.

[5]

CHEAH N P, BORST S, HENDRICKX L, et al. Effect of adding sugar to burley tobacco on the emission of aldehydes in mainstream tobacco smoke [J]. Tobacco Regulatory Science, 2018(2): 61-72.

[6]

朱尊权．烤烟质量和使用价值的关系[J]．烟草科技，1991（2）：2-4.

ZHU Zunquan. The relationship between the quality and use value of flue-cured tobacco [J]. Tobacco Science &Technology, 1991(2): 2-4.

[7]

李金兰，王道铨，罗登炎，等．不同部位烟叶的叶丝烘焙特性[J]．食品与机械，2021，37（4）：195-199，211.

LI Jinlan, WANG Daoquan, LUO Dengyan, et al. Study on toasting characteristics of different parts of tobacco [J]. Food & Machinery, 2021, 37(4): 195-199, 211.

[8]

CHO H K, PAEK K H. Feasibility in grading the burley type dried tobacco leaf using computer vision [J]. Journal of the Korean Society for Agricultural Machinery (Korea Republic), 1997, 22(1).

[9]

周文，韩力群，李锐．计算机图像处理技术在烤烟烟叶形状特征提取中的应用[J]．烟草科技，2000（1）：12-13，42．

[10]

史龙飞，宋朝鹏，贺帆，等．基于机器视觉技术的烤烟鲜烟叶成熟度检测[J]．湖南农业大学学报（自然科学版），2012，38（4）：446-450.

SHI Longfei, SONG Chaopeng, HE Fan, et al. Determination of the maturity grades of fresh leaves for flue-cured tobacco [J]. Hunan Agricultural University(Natural Sciences), 2012, 38(4): 446-450.

[11]

王杰，毕浩洋．基于极限学习机的烟叶成熟度分类[J]．烟草科技，2013（5）：17-19.

WANG Jie, BI Haoyang. Tobacco leaf maturity classification based on extreme learning machine [J]. Tobacco Science & Technology, 2013(5): 17-19.

[12]

张丽．基于视觉识别的鲜烟叶分拣系统的研究[D]．昆明：昆明理工大学，2015.

ZHANG Li. Research of tobacco leaves sorting system based on visual identification [D]. Kunming: Kunming University of Science and Technology, 2015.

[13]

谢滨瑶，祝诗平，黄华．基于BPNN和SVM的烟叶成熟度鉴别模型[J]．中国烟草学报，2019，25（1）：45-50.

XIE Binyao, ZHU Shiping, HUANG Hua. Model for identification of tobacco leaf maturity based on BPNN and SVM [J]. Acta Tabacaria Sinica, 2019, 25(1): 45-50.

[14]

徐昭梅，高云才，黄云雯，等．玉溪烟区K326不同部位初烤烟叶面形态特征的识别[J]．安徽农业科学，2018，46（10）：1-4.

XU Zhaomei, GAO Yuncai, HUANG Yunwen, et al. Characteristics identification of leaf shape in stalk position of flue-cured tobacco K326 grown in yuxi area [J]. Journal of Anhui Agricultural Sciences, 2018, 46(10): 1-4.

[15]

韩小渊，范磊，卢晓延，等．主脉特征在烟叶部位识别中的应用[J]．烟草科技，2017，50（2）：22-26.

HAN Xiaoyuan, FAN Lei, LU Xiaoyan, et al. The role of midrib of tobacco leaves in stalk position recognition [J]. Tobacco Science & Technology, 2017, 50(2): 22-26.

[16]

吴碧巧，邢永鑫，王天一．基于VGG16和迁移学习的高分辨率掌纹图像识别[J]．智能计算机与应用，2021，11（5）：37-42．

WU Biqiao, XING Yongxin, WANG Tianyi. High-resolution palmprint image recognition based on VGG16 and transfer learning [J]. Intelligent Computer and Applications, 2021, 11(5): 37-42.

[17]

张辉，胡军，石航，等．融合远端深度学习识别模型的白菜株心精准对靶喷雾系统[J]．智慧农业（中英文），2024，6（6）：85-95.

ZHANG Hui, HU Jun, SHI Hang, et al. Precision target spraying system integrated with remote deep learning recognition model for cabbage plant centers [J]. Smart Agriculture, 2024, 6(6): 85-95.

[18]

罗友璐，潘勇浩，夏顺兴，等．基于改进YOLOv8的苹果叶病害轻量化检测算法[J]．智慧农业（中英文），2024，6（5）：128-138.

LUO Youlu, PAN Yonghao, XIA Shunxing, et al. Lightweight apple leaf disease detection algorithm based on improved YOLOv8 [J]. Smart Agriculture, 2024, 6(5): 128-138.

[19]

孙道宗，张振宇，陈俊聪，等．一种基于深度学习的端到端生菜无损鲜重估测模型的建立[J]．南京农业大学学报，2024，47（6）：1212-1220.

SUN Daozong, ZHANG Zhenyu, CHEN Juncong, et al. A model for end-to-end non-destructive fresh weight estimation of lettuce based on deep learning [J]. Journal of Nanjing Agricultural University, 2024, 47(6): 1212-1220.

[20]

MATTHEW ZEILER D, ROB F. Visualizing and understanding convolutional neural networks [C]//Proceedings of the European Conference on Computer Vision, Zurich, Switzerland. 2014: 6-12.

[21]

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [J]. arXiv preprint arXiv: 1409.1556, 2014.

[22]

LOPEZ-ANTEQUERA M, GOMEZ-OJEDA R, PETKOV N, et al. Appearance-invariant place recognition by discriminatively training a convolutional neural network [J]. Pattern Recognition Letters, 2017, 92: 89-95.

[23]

SHIN H C, ROTH H R, GAO M C, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning [J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1285-1298.

[24]

WANG H, WANG Z, DU M, et al. Score-CAM: Score-weighted visual explanations for convolutional neural networks [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020: 24-25.

2025年第6卷第2期

预览PDF | 下载PDF

引用本文

BibTeX

文章信息

doi: 10.12398/j.issn.2096-7217.2025.02.007

接收时间：2024-07-11
首发时间：2026-11-05
出版时间：2025-05-15

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2024-07-11
修回日期：2024-09-08

基金

National Natural Science Foundation of China(32360579)

国家自然科学基金项目(32360579)

Key Scientific Research Project of Hunan Provincial Department of Education(20A230)

湖南省教育厅重点项目(20A230)

Science and Technology Project of Hunan Tobacco Company Hengyang Branch(2021430481240017)

湖南省烟草公司衡阳市公司科技项目(2021430481240017)

作者信息

^1.湖南省烟草公司衡阳市公司，湖南衡阳，421000

^2.湖北中烟工业有限责任公司，湖北武汉，430040

^3.湖南农业大学食品科学技术学院，湖南长沙，410128

^4.食品科学与生物技术湖南省重点实验室，湖南长沙，410128

^5.麻省大学阿莫斯特分校食品科学系，美国马萨诸塞州阿莫斯特，01003

通讯作者:

^* 范伟，男，1983年生，河北邢台人，博士，讲师；研究方向为农产品加工智能检测。E-mail：weifan@hunau.edu.cn

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/znhnyzbxb/CN/10.12398/j.issn.2096-7217.2025.02.007

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT