Identifying apple leaf diseases using improved EfficientNet

WANG Ruipeng; CHEN Fengjun; ZHU Xueyan; ZHANG Xinwei

doi:10.11975/j.issn.1002-6819.202306140

Volume 39 Issue 18

Sep. 2023

Turn off MathJax

Article Contents

Abstract

References

Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE) > 2023 > 39(18): 201-210. > DOI: 10.11975/j.issn.1002-6819.202306140

WANG Ruipeng, CHEN Fengjun, ZHU Xueyan, ZHANG Xinwei. Identifying apple leaf diseases using improved EfficientNet[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(18): 201-210. DOI: 10.11975/j.issn.1002-6819.202306140

Citation:

PDF (2331 KB)

Identifying apple leaf diseases using improved EfficientNet

WANG Ruipeng^{1, 2,},
CHEN Fengjun^{1, 2, 3, ,},
ZHU Xueyan^{1, 4},
ZHANG Xinwei^{1, 5}

1.
School of Technology, Beijing Forestry University, Beijing 100083, China
2.
National Key Laboratory-Forest Resource Efficient Production, Beijing 100083, China
3.
Beijing Laboratory of Urban and Rural Ecological Environment, Beijing 100083, China
4.
Key Laboratory of State Forestry Administration for Forestry Equipment and Automation, Beijing, 100083, China
5.
Research Center for Intelligent Forestry, Beijing 100083, China

More Information

Received Date: June 19, 2023
Revised Date: September 18, 2023
Available Online: October 26, 2023

Graphical Abstract

Abstract

Abstract

The traditional manual control measures for apple disease primarily rely on subjective experience, which can lead to arbitrariness and bias. This approach is also prone to pesticide waste and misuse. As apple leaves are one of the high-incidence areas of diseases, achieving natural environment-based identification of apple leaf diseases can provide effective guidance for disease prevention and control. To address the challenge of accurate identification of apple leaf diseases in natural settings, a DenseNet121+EfficientNet model with Focal Loss and Label Smoothing (DEFL) is designed. Given that apple leaf disease lesions are small and exhibit varying spatial characteristics for different diseases, accurately localizing and identifying disease regions is challenging. The DEFL model utilizes two parallel networks: EfficientNet-B0 and DenseNet121 for feature extraction. It combines the semantic and positional information extracted from these networks to enhance the model's fine-grained feature extraction capability. To overcome difficulties in identifying apple leaf samples due to the similarity in features among different diseases, a Focal Loss function, combined with label smoothing strategies, is introduced. This prevents the model from being overly confident about the class of apple leaf samples, focusing on those samples with challenging decision boundaries during training, thereby improving the model's ability to recognize boundary cases and enhancing its robustness and generalization. The DEFL model proposed in this study was tested with 3906 apple leaf disease images in natural scenes. The results show that the overall recognition accuracy of the model proposed in this study is 99.13%, and the mean average accuracy is 98.47%. The results of ablation experiments show that the mean average precision of the model is improved by 7.99% after adding DenseNet121 feature extraction branch to EfficientNet-B0. And, after introducing the focus loss function combined with label smoothing strategy to EfficientNet-B0, the mean average precision of the model is improved by 3.15%. After the combination of the two improvements, the mean average precision of the model increased by 12.29%. Visualization results using Gradient-weighted class activation mapping (Grad-CAM) heatmaps show that the model accurately localizes and focuses on disease regions. The image feature information used by the model for apple leaf disease recognition is reliable. Uniform manifold approximation and projection (UMAP) feature dimension reduction visualization results indicate that the Focal Loss function with label smoothing effectively enhances the model's feature extraction capability, resulting in more distinctive feature information and improved disease recognition. The comparative experimental results show that compared with mainstream recognition models such as ResNet50, Inception V3, and ResNeXt, as well as EfficientNet-B0 models that fuse these three models, the mean average precision of the proposed model has increased by 14.53, 13.17, 14.61, 6.4, 7.71, and 8.91 percentage points, respectively, and the model size has decreased by 18.73, 7.7, 12.2, 83.62, 69.6, and 60.09 MB, respectively. Comparative experiments have shown that the proposed model has the best recognition performance. In practical applications, the DEFL model achieved an overall recognition accuracy of 97.73% and a mean average precision of 95.82% when tested with 1501 apple leaf images collected from apple plantations. In conclusion, the DEFL model proposed in this study enables accurate and rapid identification of apple leaf diseases, providing valuable guidance for apple disease prevention and control.
- disease; image recognition,
- apple leaf,
- EfficientNet,
- DenseNet121

FullText(HTML)

References (43)

References

[1]	LIANG X, ZHANG R, GLEASON M L, et al. Sustainable apple disease management in China: Challenges and future directions for a transforming industry[J]. Plant Disease, 2022, 106(3): 786-799. doi: 10.1094/PDIS-06-21-1190-FE
[2]	GAVHALE K R, GAWANDE U, HAJARI K O. Unhealthy region of citrus leaf detection using image processing techniques[C]//International Conference for Convergence for Technology-2014. IEEE, Pune, India, 2014: 1-6.
[3]	HLAING C S, ZAW S M M. Tomato plant diseases classification using statistical texture feature and color feature[C]//2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS). IEEE, Singapore, 2018: 439-444.
[4]	刘立波,周国民. 基于多层感知神经网络的水稻叶瘟病识别方法[J]. 农业工程学报,2009,25(13):213-217. LIU Libo, ZHOU Guomin. Identification method of rice leaf blast using multilayer perception neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2009, 25(13): 213-217. (in Chinese withEnglish abstract)
[5]	王献锋,张善文,王震,等. 基于叶片图像和环境信息的黄瓜病害识别方法[J]. 农业工程学报,2014,30(14):148-153. WANG Xianfeng, ZHANG Shanwen, WANG Zhen, et al. Recognition of cucumber diseases based on leaf image and environmental information[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(14): 148-153. (in Chinese withEnglish abstract)
[6]	张建华,孔繁涛,李哲敏,等. 基于最优二叉树支持向量机的蜜柚叶部病害识别[J]. 农业工程学报,2014,30(19):222-231. ZHANG Jianhua, KONG Fantao, LI Zhemin, et al. Recognition of honey pomelo leaf diseases based on optimal binary tree support vector machine[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(19): 222-231. (in Chinese withEnglish abstract)
[7]	张善文,张传雷. 基于局部判别映射算法的玉米病害识别方法[J]. 农业工程学报,2014,30(11):167-172. ZHANG Shanwen, ZHANG Chuanlei. Maize disease recognition based on local discriminant algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(11): 167-172. (in Chinese withEnglish abstract)
[8]	FENG J, Li H N, YANG W P, et al. Horticultural plant diseases multispectral classification using combined classified methods[J]. Spectroscopy and Spectral Analysis, 2010, 30(2): 426-429.
[9]	ES-SSADY Y, El MASSI I, El YASSA M, et al. Automatic recognition of plant leaves diseases based on serial combination of two SVM classifiers[C]//2016 International Conference on Electrical and Information Technologies (ICEIT). IEEE, Tangiers, Morocco, 2016: 561-566.
[10]	GUI J, HAO L, ZHANG Q, et al. A new method for soybean leaf disease detection based on modified salient regions[J]. International Journal of Multimedia and Ubiquitous Engineering, 2015, 10(6): 45-52. doi: 10.14257/ijmue.2015.10.6.06
[11]	田有文,李天来,李成华,等. 基于支持向量机的葡萄病害图像识别方法[J]. 农业工程学报,2007,23(6):175-180. TIAN Youwen, LI Tianlai, LI Chenghua, et al. Method for recognition of grape disease based on support vector machine[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2007, 23(6): 175-180. (in Chinese withEnglish abstract)
[12]	CHUANLEI Z, SHANWEN Z, JUCHENG Y, et al. Apple leaf disease identification using genetic algorithm and correlation based feature selection method[J]. International Journal of Agricultural and Biological Engineering, 2017, 10(2): 74-83.
[13]	GAYATHRI DEVI T, NEELAMEGAM P. Image processing based rice plant leaves diseases in Thanjavur, Tamilnadu[J]. Cluster Computing, 2019, 22: 13415-13428. doi: 10.1007/s10586-018-1949-x
[14]	ZHANG Y, HUANG S, ZHOU G, et al. Identification of tomato leaf diseases based on multi-channel automatic orientation recurrent attention network[J]. Computers and Electronics in Agriculture, 2023, 205: 107605. doi: 10.1016/j.compag.2022.107605
[15]	DESHPANDE R, PATIDAR H. Tomato plant leaf disease detection using generative adversarial network and deep convolutional neural network[J]. The Imaging Science Journal, 2022, 70(1): 1-9. doi: 10.1080/13682199.2022.2161696
[16]	GADEKALLU T R, RAJPUT D S, REDDY M P K, et al. A novel PCA–whale optimization-based deep neural network model for classification of tomato plant diseases using GPU[J]. Journal of Real-Time Image Processing, 2021, 18: 1383-1396. doi: 10.1007/s11554-020-00987-8
[17]	ANANDHAKRISHNAN T, MURUGAIVAN J S M. Identification of tomato leaf disease detection using pretrained deep convolutional neural network models[J]. Scalable Computing:Practice and Experience, 2020, 21(4): 625-635. doi: 10.12694/scpe.v21i4.1780
[18]	WU Q, CHEN Y, MENG J. DCGAN-based data augmentation for tomato leaf disease identification[J]. IEEE Access, 2020, 8: 98716-98728. doi: 10.1109/ACCESS.2020.2997001
[19]	苏仕芳,乔焰,饶元. 基于迁移学习的葡萄叶片病害识别及移动端应用[J]. 农业工程学报,2021,37(10):127-134. SU Shifang, QIAO Yan, RAO Yuan. Recognition of grape leaf diseases and mobile application based on transfer learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(10): 127-134. (in Chinese withEnglish abstract)
[20]	曹跃腾,朱学岩,赵燕东,等. 基于改进ResNet的植物叶片病虫害识别[J]. 中国农机化学报,2021,42(12):175-181. CAO Yueteng, ZHU Xueyan, ZHAO Yandong, et al. Recognition of plant leaf diseases and insect pests based on improved ResNet[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(12): 175-181. (in Chinese withEnglish abstract)
[21]	NADER A, KHAFAGV M H, HUSSIEN S A. Grape leaves diseases classification using ensemble learning and transfer learning[J]. International Journal of Advanced Computer Science and Applications, 2022, 13(7): 563-571.
[22]	HAQUE M A, MARWAHA S, ARORA A, et al. A lightweight convolutional neural network for recognition of severity stages of maydis leaf blight disease of maize[J]. Frontiers in Plant Science, 2022, 13: 1077568. doi: 10.3389/fpls.2022.1077568
[23]	MA Z, WANG Y, ZHANG T, et al. Maize leaf disease identification using deep transfer convolutional neural networks[J]. International Journal of Agricultural and Biological Engineering, 2022, 15(5): 187-195. doi: 10.25165/j.ijabe.20221505.6658
[24]	SHARMA R, SINGH A, JHANIHI N Z, et al. Plant disease diagnosis and image classification using deep learning[J]. Computers, Materials and Continua, 2022, 71(2): 2125-2140. doi: 10.32604/cmc.2022.020017
[25]	ELFATIMI E, ERVIGIT R, ELFATIMI L. Beans leaf diseases classification using mobilenet models[J]. IEEE Access, 2022, 10: 9471-9482. doi: 10.1109/ACCESS.2022.3142817
[26]	张国忠,吕紫薇,刘浩蓬,等. 基于改进DenseNet和迁移学习的荷叶病虫害识别模型[J]. 农业工程学报,2023,39(8):188-196. ZHANG Guozhong, LYU Ziwei, LIU Haopeng, et al. Model for identifying lotus leaf pests and diseases using improved DenseNet and transfer learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(8): 188-196. (in Chinese withEnglish abstract)
[27]	李子茂,徐杰,郑禄,等. 基于改进DenseNet的茶叶病害小样本识别方法[J]. 农业工程学报,2022,38(10):182-190. LI Zimao, XU Jie, ZHENG Lu, et al. Small sample recognition method of tea disease based on improved DenseNet[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(10): 182-190. (in Chinese withEnglish abstract)
[28]	RAI C K, PAHUIA R. Classification of Diseased Cotton Leaves and Plants Using Improved Deep Convolutional Neural Network[J]. Multimedia Tools and Applications, 2023, 82(16): 25307-25325.
[29]	RAJPOOT V, TIWARI A, JALAL A S. Automatic early detection of rice leaf diseases using hybrid deep learning and machine learning methods[J]. Multimedia Tools and Applications, 2023, 82(23): 36091-36117.
[30]	李想,胡肖楠,李方一,等. 苹果树叶多病害及不可辨别病害的轻量识别算法[J]. 农业工程学报,2023,39(14):184-190. LI Xiang, HU Xiaonan, LI Fangyi, et al. Lightweight recognition for multiple and indistinguishable diseases of apple tree leaf[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(14): 184-190. (in Chinese withEnglish abstract)
[31]	李大湘,滑翠云,刘颖. 面向苹果叶部病害识别的细粒度蒸馏模型[J]. 农业工程学报,2023,39(7):185-194. LI Daxiang, HUA Cuiyun, LIU Ying. Identifying apple leaf disease using a fine-grained distillation model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(7): 185-194. (in Chinese withEnglish abstract)
[32]	刘斌,贾润昌,朱先语,等. 面向移动端的苹果叶部病虫害轻量级识别模型[J]. 农业工程学报,2022,38(6):130-139. LIU Bin, JIA Runchang, ZHU Xianyu, et al. Lightweight identification model for apple leaf diseases and pests based on mobile terminals[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(6): 130-139. (in Chinese withEnglish abstract)
[33]	YADAV A, THAKUR U, SAXENA R, et al. AFD-Net: Apple foliar disease multi classification using deep learning on plant pathology dataset[J]. Plant and Soil, 2022, 477(1/2): 595-611. doi: 10.1007/s11104-022-05407-3
[34]	XU C, WANG X, ZHANG S. Dilated convolution capsule network for apple leaf disease identification[J]. Convolutional Neural Networks and Deep Learning for Crop Improvement and Production, 2023, 16648714: 182.
[35]	李大湘,曾小通,刘颖. 耦合全局与局部特征的苹果叶部病害识别模型[J]. 农业工程学报,2022,38(16):207-214. LI Daxiang, ZENG Xiaotong, LIU Ying. Apple leaf disease identification model by coupling global and patch features[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(16): 207-214. (in Chinese withEnglish abstract)
[36]	YU H, CHENG X, CHEN C, et al. Apple leaf disease recognition method with improved residual network[J]. Multimedia Tools and Applications, 2022, 81(6): 7759-7782. doi: 10.1007/s11042-022-11915-2
[37]	徐艳蕾,孔朔琳,陈清源,等. 基于Transformer的强泛化苹果叶片病害识别模型[J]. 农业工程学报,2022,38(16):198-206. XU Yanlei, KONG Shuolin, CHEN Qingyuan, et al. Model for identifying strong generalization apple leaf disease using Transformer[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(16): 198-206. (in Chinese withEnglish abstract)
[38]	TAN M, LE Q. Efficientnet: Rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning. PMLR, Long Beach, California, USA, 2019: 6105-6114.
[39]	HUANG G, LIU Z, VAN Der MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 2017: 4700-4708.
[40]	THAPA R; ZHANG K; SNAVELY N; et al. Plant Pathology 2021 - FGVC8[N/OL]. (2021-03-16)[2023-06-20]. https://kaggle.com/competitions/plant-pathology-2021-fgvc8
[41]	LIN T Y, ROYCHOWDHURY A, MAJI S. Bilinear CNN models for fine-grained visual recognition[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 1449-1457.
[42]	SELVARAIU R R, COGSWELL M, DAS A, et al. Grad-cam: Visual explanations from deep networks via gradient-based localization[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy, 2017: 618-626.
[43]	BECHT E, MCLNNES L, HEALY J, et al. Dimensionality reduction for visualizing single-cell data using UMAP[J]. Nature Biotechnology, 2019, 37(1): 38-44. doi: 10.1038/nbt.4314

Cited By

Cited by

Periodical cited type(12)

1.	陈自立，林卫，贺佳，王来刚，郑国清，彭一龙，焦家东，郭燕. 基于卷积神经网络的农作物病害识别研究. 中国农业科技导报(中英文). 2025(04): 99-109 .
2.	刘宇雄，兰艳亭，陈晓栋. 基于级联式分组注意力机制的葡萄病害识别模型. 江苏农业科学. 2025(05): 121-128 .
3.	杨宏宇，谢小龙，郭容，张佳进. 基于EBS-YOLO v7的轻量化葡萄病害识别方法. 江苏农业科学. 2025(05): 165-174 .
4.	向玉云，陈思远，高爽，李书琴. 基于自适应BayesShrink和频-空特征融合的作物病害识别方法. 农业工程学报. 2025(06): 204-215 . 本站查看
5.	杨子奕，崔善柠，曲大义，杨宇翔，刘朝晖. 基于YOLOv5的动态车牌识别及残差网络优化方法. 青岛理工大学学报. 2025(02): 115-123 .
6.	郭惠萍，曹亚州，王晨思，荣麟瑞，李怡，王霆伟，杨福增. 基于迁移学习的苹果落叶病识别与应用. 农业工程学报. 2024(03): 184-192 . 本站查看
7.	李冬睿，邱尚明，杨善友. 基于自适应权重优化的多任务深度学习模型在甘蔗病害识别中的应用. 智能计算机与应用. 2024(03): 163-167 .
8.	熊晓菲，王秀琴，庄翠珍，郭家贤，谢新锐，吴建伟，李奇峰. 基于ROI融合特征的柑橘炭疽病诊断方法. 中国农业科技导报. 2024(09): 83-92 .
9.	周罕觅，陈佳庚，代智光，马林爽，秦龙，李纪琛，苏裕民，向友珍. 基于知识蒸馏和轻量级卷积神经网络的植物病害识别方法. 南京农业大学学报. 2024(06): 1189-1201 .
10.	黄贻望，王国帅，毛志，刘声. KMeans++与注意力机制融合的苹果叶片病害识别方法. 江苏农业科学. 2024(20): 190-198 .
11.	白少文，周济华，董毅，张键锋，施亮，杨坤. 基于EfficientNet-B4模型的云南省湖北钉螺滇川亚种视觉智能识别模型的建立. 中国血吸虫病防治杂志(中英文). 2024(06): 555-561 .
12.	黄铝文，关非凡，谦博，侯闳耀，刘迎庆，李雯敏. 基于2D DWT与MobileNetV3融合的轻量级茶叶病害识别. 农业工程学报. 2023(24): 207-214 . 本站查看