基于改进GoogLeNet的玉米叶片病害识别及其可解释性研究

doi:10.13733/j.jcam.issn.2095-5553.2025.01.031

摘要/Abstract

摘要： 为加强农作物病害的识别，减少病害发生的频率与强度，提高农作物产量与品质，基于迁移学习构建5种深度学习网络，对玉米叶片锈病、大小斑病和灰斑病进行识别分类研究。通过对比AlexNet、VGG19、ResNet50、GoogLeNet和MobileNetV2深度学习网络，GoogLeNet的识别准确率最高，达到96.3%，模型收敛效果最好。通过进一步优化GoogLeNet模型架构，在inception模块中插入卷积注意力模块CBAM，使用LeakyReLU激活函数替换ReLU函数，改进后网络通道注意力增强，测试集的识别准确率达到99.0%，识别准确率提高2.7%。采用CAM和LIME算法对模型的可解释性分析，改进后网络的可解释性增强，更好地关注叶片病害部分。

关键词: 深度学习, 玉米叶片病害, 迁移学习, 可解释性, 图像处理

Abstract: In order to strengthen the identification of crop diseases, reduce the frequency and intensity of disease occurrence, and increase crop yield and quality, five kinds of deep learning frameworks based on transfer learning was used to identify and classify maize leaf diseases, including corn rust, leaf blight and gray spot. Compared with AlexNet, VGG19, ResNet50, GoogLeNet and MobileNetV2 deep learning networks, the recognition accuracy of GoogLeNet is the highest by 96.3%, and the model convergence effect is the best. By further optimizing the GoogLeNet model architecture, the Convolutional Block Attention Module (CBAM) is inserted into the inception module, and the LeakyReLU activation function is used to replace the ReLU function. After the improvement, the network channel attention is strengthened, the recognition accuracy of the test dataset reaches 99.0%, and the recognition accuracy is increased by 2.7%. CAM(Class Activation Mapping) and LIME(Local Interpretable Model-Agnostic Explanations) algorithms are used to analyze the model interpretability, the interpretability of the improved network shows higher explainability, with more attention on disease affected leaf regions.

Key words: deep learning, maize leaf disease, transfer learning, explainability, image processing

中图分类号:

牛潘婷, 张宝林, 潘丽杰, 郭建鹏(. 基于改进GoogLeNet的玉米叶片病害识别及其可解释性研究[J]. 中国农机化学报, 2025, 46(1): 204-212.

Niu Panting, Zhang Baolin, , , Pan Lijie, Guo Jianpeng. Identification and explainability of maize leaf diseases based on improved GoogLeNet#br#[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(1): 204-212.

参考文献

［1］　刘丽娟, 刘仲鹏, 张丽梅. 基于图像处理技术的玉米叶部病害识别研究［J］. 吉林农业科学, 2014, 39(1): 61-65.Liu Lijuan, Liu Zhongpeng, Zhang Limei. Studies on image processing of maize leaf diseases ［J］. Journal of Jilin Agricultural Sciences, 2014, 39(1): 61-65.
［2］　翟肇裕, 曹益飞, 徐焕良, 等. 农作物病虫害识别关键技术研究综述［J］. 农业机械学报, 2021, 52(7): 1-18.
Zhai Zhaoyu, Cao Yifei, Xu Huanliang, et al. Review of key techniques for crop disease and pest detection ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(7): 1-18.
［3］　Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks ［C］.Advances in Neural Information Processing Systems, 2012.
［4］　Simonyan K, Zisserman A. Very deep convolutional networks for largescale image recognition ［J］. arXiv preprint arXiv: 1409. 1556, 2014.
［5］　Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions ［C］. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
［6］　He K, Zhang X, Ren S, et al. Deep residual learning for image recognition ［C］. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
［7］　Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks ［C］. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
［8］　Howard A, Zhu M, Chen B, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications ［J］. arXiv preprint arXiv: 1704. 04861, 2017.
［9］　宋晨勇, 白皓然, 孙伟浩, 等. 基于GoogLeNet改进模型的苹果叶病诊断系统设计［J］. 中国农机化学报, 2021, 42(7): 148-155.
Song Chenyong, Bai Haoran, Sun Weihao, et al. Design of apple leaf disease diagnosis system based on GoogLeNet improved model ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(7): 148-155.
［10］　李恩霖, 谢秋菊, 苏中滨, 等. 基于深度学习的玉米叶片病斑识别方法研究［J］. 智慧农业导刊, 2021, 1(10): 1-10.Li Enlin, Xie Qiuju, Su Zhongbin, et al. Research on maize leaf disease spot recognition based on deep learning ［J］. Journal of Smart Agriculture, 2021, 1(10): 1-10.
［11］　许景辉, 邵明烨, 王一琛, 等. 基于迁移学习的卷积神经网络玉米病害图像识别［J］. 农业机械学报, 2020, 51(2): 230-236.
Xu Jinghui, Shao Mingye, Wang Yichen, et al. Recognition of corn leaf spot and rust based on transfer learning with convolutional neural network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(2): 230-236.
［12］　李静, 陈桂芬, 安宇. 基于优化卷积神经网络的玉米螟虫害图像识别［J］. 华南农业大学学报, 2020, 41(3): 110-116.Li Jing, Chen Guifen, An Yu. Image recognition of pyrausta nubilalis based on optimized convolutional neural network ［J］. Journal of South China Agricultural University, 2020, 41(3): 110-116.
［13］　杨长磊, 李彩林, 王佳文, 等. 基于改进深度神经网络的农作物病害识别研究［J］. 农业与技术, 2021, 41(6): 1-3.
［14］　Mohanty S P, Hughes D P, Salathé M. Using deep learning for imagebased plant disease detection ［J］. Frontiers in Plant Science, 2016, 7: 1419.
［15］　杨朋波, 桑基韬, 张彪, 等. 面向图像分类的深度模型可解释性研究综述［J］. 软件学报, 2023, 34(1): 230-254.Yang Pengbo, Sang Jitao, Zhang Biao, et al. Survey on interpretability of deep models for image classification ［J］. Journal of Software, 2023, 34(1): 230-254.
［16］　陈冲, 陈杰, 张慧, 等. 深度学习可解释性综述［J］. 计算机科学, 2023, 50(5): 52-63.Chen Chong, Chen Jie, Zhang Hui, et al. A Review of interpretability in deep learning ［J］. Computer Science, 2023, 50(5): 52-63.
［17］　Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization ［C］. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
［18］　Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: Visual explanations from deep networks via gradientbased localization ［C］. 2017 IEEE International Conference on Computer Vision (ICCV), 2017.
［19］　Ribeiro M T, Singh S, Guestrin C. “Why should i trust you?” explaining the predictions of any classifier ［C］. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 1135-1144.
［20］　庄福振, 罗平, 何清, 等. 迁移学习研究进展［J］. 软件学报, 2015, 26(1): 26-39.Zhuang Fuzhen, Luo Ping, He Qing, et al. Survey on transfer learning research ［J］. Journal of Software, 2015, 26(1): 26-39.
［21］　Ishengoma F S, Rai I A, Said R N. Identification of maize leaves infected by fall armyworms using UAVbased imagery and convolutional neural networks ［J］. Computers and Electronics in Agriculture, 2021, 184: 106124.
［22］　苏炯铭, 刘鸿福, 项凤涛, 等. 深度神经网络解释方法综述［J］. 计算机工程, 2020, 46(9): 1-15.Su Jiongming, Liu Hongfu, Xiang Fengtao, et al. Survey of interpretation methods for deep neural networks ［J］. Computer Engineering, 2020, 46(9): 1-15.
［23］　Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: Visual explanations from deep networks via gradientbased localization ［C］. IEEE International Conference on Computer Vision. IEEE, 2017.
［24］　Smilkov D, Thorat N, Kim B, et al. SmoothGrad: Removing noise by adding noise ［J］. arXiv Preprint arXiv: 1706. 03825, 2017.
［25］　Woo S, Park J, Lee J, et al. CBAM: Convolutional block attention module ［C］. Proceedings of the 15th European Conference on Computer Vision (ECCV), 2018.
［26］　张俊宁, 毕泽洋, 闫英, 等. 基于注意力机制与改进YOLO的温室番茄快速识别［J］. 农业机械学报, 2023, 54(5): 236-243.
Zhang Junning, Bi Zeyang, Yan Ying, et al. Fast recognition of greenhouse tomato targets based on attention mechanism and improved YOLO ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(5): 236-243.
［27］　王昕, 董琴, 杨国宇. 基于优化CBAM改进YOLOv5的农作物病虫害识别［J］. 计算机系统应用, 2023, 32(7): 261-268.Wang Xin, Dong Qin, Yang Guoyu. YOLOv5 improved by optimized CBAM for crop pest identification ［J］. Computer Systems & Applications, 2023, 32(7): 261-268.
［28］　卫雅娜, 王志彬, 乔晓军, 等. 基于注意力机制与EfficientNet的轻量化水稻病害识别方法［J］. 中国农机化学报, 2022, 43(11): 172-181.
Wei Yana, Wang Zhibin, Qiao Xiaojun, et al. Lightweight rice disease identification method based on attention mechanism and EfficientNet ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(11): 172-181.
［29］　张瑞青, 李张威, 郝建军, 等. 基于迁移学习的卷积神经网络花生荚果等级图像识别［J］. 农业工程学报, 2020,36(23): 171-180.Zhang Ruiqing, Li Zhangwei, Hao Jianjun, et al. Image recognition of peanut pod grades based on transfer learning with convolutional neural network ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(23): 171-180.
［30］　周慧升. 玉米灰斑病的发生及综合防治［J］. 云南农业, 2020(8): 56-58.
［31］　于雪莹, 高继勇, 王首程, 等. 基于生成对抗网络和混合注意力机制残差网络的苹果病害识别［J］. 中国农机化学报, 2022, 43(6): 166-174.
Yu Xueying, Gao Jiyong， Wang Shoucheng, et al. Apple disease recognition based on wassersteingenerative adversarialnetworks and hybrid attention mechanism residual network ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(6): 166-174.

[1]	夏子林, 张新洲, 王文波, 夏先飞, 陈兰, 顾寄南. 基于机器视觉的蚕豆荚高精度检测方法研究[J]. 中国农机化学报, 2025, 46(1): 157-163.
[2]	李春雨, 郭肖琴, 杨晶晶, 李忠华. 基于深度学习的水果图像识别[J]. 中国农机化学报, 2025, 46(1): 198-203.
[3]	彭勇, 乔印虎, 张春燕, 姚杰, 包殿令. 改进YOLOv5模型的草莓检测方法研究[J]. 中国农机化学报, 2025, 46(1): 213-219.
[4]	赵爽, 俞永强, 苗玉彬, 刘可心 . 基于改进 Mask R-CNN的青菜杂质检测研究[J]. 中国农机化学报, 2024, 45(9): 77-82.
[5]	杨浩勇 , 王超柱 , 刘浩义 , 关心桐 , 刘璎瑛 , 丁永前 . 种子破损率快速检测方法研究[J]. 中国农机化学报, 2024, 45(9): 104-110.
[6]	韩鹏飞, 宋其江, 贾梦实. 基于改进轻量化 EfficientNet-V2模型的小麦种子分类[J]. 中国农机化学报, 2024, 45(9): 111-117.
[7]	李志臣, 凌秀军, 李鸿秋. 基于声音深度学习的发动机失火故障诊断[J]. 中国农机化学报, 2024, 45(9): 134-140.
[8]	桑一男 , 徐增莱 , 汪琼 , 葛海涛 , 王殿广 . 一种轮式采花机器人设计——以黄蜀葵为例[J]. 中国农机化学报, 2024, 45(9): 202-208.
[9]	李邦国, 王辉, 宋杨, 任志伟, 刘跃华, 徐乐程. 基于无人驾驶小麦收割机立体视觉感知系统[J]. 中国农机化学报, 2024, 45(9): 244-249.
[10]	宋小鹿 , 冯娟 , 梁翔宇 , 周玺兴 . 基于 YOLOv4的水下海参检测与计数算法[J]. 中国农机化学报, 2024, 45(9): 258-264.
[11]	许贞辉, 李晓娟. 果园树干检测与导航线拟合算法研究[J]. 中国农机化学报, 2024, 45(8): 217-222.
[12]	苏斐, 王光辉, 史艳霞, 贾然, 闫银发, 祖林禄, . 融合通道注意力机制的ResUnet作物病斑分割模型[J]. 中国农机化学报, 2024, 45(8): 228-233.
[13]	胡国玉, 刘广, 周星光, 董娅兰, 周建平, . 基于Swin-TDL算法的果园环境下葡萄病害检测方法[J]. 中国农机化学报, 2024, 45(8): 234-239.
[14]	张延军, 赵建鑫, . 基于多路神经网络的黄花菜关节点检测算法研究[J]. 中国农机化学报, 2024, 45(7): 228-234.
[15]	吴利刚, 吕媛媛, 周倩, 陈乐, 张梁, 史建华. 基于改进YOLOv5的轻量级黄花成熟检测方法[J]. 中国农机化学报, 2024, 45(7): 235-242.