Optimized Deep Learning Model for Soybean Leaf Classification in Complex Field Environments

Jiwoo Kang; Taehwan Shin; Jonghan Ko

doi:10.7740/kjcs.2025.70.2.068

All Issue

2025 Vol.70, Issue 2 Preview Page Next Page

Original Research Article

Optimized Deep Learning Model for Soybean Leaf Classification in Complex Field Environments

1 June 2025. pp. 68-78

PDF XML

Abstract

Accurate and efficient monitoring of soybean crops is crucial to ensure a stable yield and improved quality. Traditional manual monitoring methods are labor-intensive and time consuming, highlighting the need for automated solutions. Deep learning models, particularly convolutional neural networks (CNNs), represent a promising approach for precise and efficient crop classification. This study introduced an optimized ResNet50 model for classifying soybean varieties using leaf images captured under complex field conditions. Data were collected from experimental fields at Chonnam National University (Gwangju) and the National Institute of Crop Science (Wanju-gun, Jeollabuk-do) between 2021 and 2022, encompassing 4,827 leaf images and 795 canopy images. The dataset was curated under various weather conditions (sunny, cloudy, and rainy), with backgrounds featuring soil, weeds, and other plants to ensure real-world variability. ResNet50 was chosen as the base model because of its robust feature extraction capabilities, and was further optimized through hyperparameter tuning and transfer learning. The final model achieved a classification accuracy of 94.5%, surpassing those of VGG16, Inception-V3, MobileNetV3, and other ResNet variants. These results underscore the effectiveness of CNN-based models in automating soybean variety classification, reducing the reliance on manual assessments, and contributing to advancements in precision agriculture and innovative farming technologies.

Keywords

convolutional neural network (CNN)

deep learning leaf classification

soybean

References

Chaki, J., R. Parekh, and S. Bhattacharya. 2015. Plant leaf recognition using texture and shape features with neural classifiers. Pattern Recognit. Lett. 58 : 61-68. https://doi.org/10.1016/j.patrec.2015.02.010

10.1016/j.patrec.2015.02.010

Deng, J., W. Dong, R. Socher, L. J. Li, L. Kai, and F.-F. Li. 2009. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 20-25 June 2009.

10.1109/CVPR.2009.5206848

Du, J.-x., C.-M. Zhai, and Q.-P. Wang. 2013. Recognition of plant leaf image based on fractal dimension features. Neurocomputing 116 : 150-156. https://doi.org/10.1016/j.neucom.2012.03.028

10.1016/j.neucom.2012.03.028

Hao, X., J. Jia, W. Gao, X. Guo, W. Zhang, L. Zheng, M. Wang 2020. MFC-CNN: An automatic grading scheme for light stress levels of lettuce (Lactuca sativa L.) leaves. Comput. Electron. Agric. 179 : 105847. https://doi.org/10.1016/j.compag.2020.105847

10.1016/j.compag.2020.105847

He, K., X. Zhang, S. Ren, and J. Sun, 2016. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778.

10.1109/CVPR.2016.9026180094

Kamilaris, A. and F.X. Prenafeta-Boldú. 2018. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture 147 : 70-90. https://doi.org/10.1016/j.compag.2018.02.016

10.1016/j.compag.2018.02.016

KKang, C., X. Yu, S. H. Wang, D. S. Guttery, H. M. Pandey, Y. Tian, and Y. D. Zhang. 2021. A heuristic neural network structure relying on fuzzy logic for images scoring. IEEE Trans. Fuzzy Syst. 29 : 34-45. doi:10.1109/TFUZZ.2020.2966163

10.1109/TFUZZ.2020.296616333408453PMC7116542

Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60 : 84-90. https://doi.org/10.1145/3065386

10.1145/3065386

Rawat, W. and Z. Wang. 2017. Deep convolutional neural networks for image classification: A comprehensive review. Neural computation 29 : 2352-2449. https://doi.org/10.1162/neco_a_00990

10.1162/neco_a_0099028599112

Sandler, M., A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen. 2018. MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE conference on computer vision and pattern recognition, 4510-4520, 18-23 June 2018.

10.1109/CVPR.2018.00474

Silva, P. F. B., A. R. S. Marçal, and R. M. A. da Silva. 2013. Evaluation of Features for Leaf Discrimination. Image Analysis and Recognition, Berlin, Heidelberg. 2013. Springer Berlin Heidelberg.

10.1007/978-3-642-39094-4_23

Simonyan, K. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Specht, J. E., B. W. Diers, R. L. Nelson, J. F. F. de Toledo, J. A. Torrion, and P. Grassini. 2014. Soybean. Yield Gains in Major U.S. Field Crops. pp. 311-355.

10.2135/cssaspecpub33.c12

Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, E. Dumitru, V. Vincent, and R. Andrew. 2015. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition, 1-9, 07-12 June 2015.

10.1109/CVPR.2015.7298594

Tavakoli, H., P. Alirezazadeh, A. Hedayatipour, A.H. Banijamali Nasib, and N. Landwehr. 2021. Leaf image-based classification of some common bean cultivars using discriminative convolutional neural networks. Comput. Electron. Agric. 181 : 105935. https://doi.org/10.1016/j.compag.2020.105935

10.1016/j.compag.2020.105935

Tiwari, S. 2020. A comparative study of deep learning models with handcraft features and non-handcraft features for automatic plant species identification. International Journal of Agricultural and Environmental Information Systems (IJAEIS) 11 : 44-57. doi:10.4018/IJAEIS.2020040104

10.4018/IJAEIS.2020040104

Turkoglu, M. and D. Hanbay. 2019. Recognition of plant leaves: An approach with hybrid features produced by dividing leaf images into two and four parts. Appl. Math. Comput. 352 : 1-14. https://doi.org/10.1016/j.amc.2019.01.054

10.1016/j.amc.2019.01.054

Waheed, A., M. Goyal, D. Gupta, A. Khanna, A. E. Hassanien, and H. M. Pandey. 2020. An optimized dense convolutional neural network model for disease recognition and classification in corn leaf. Comput. Electron. Agric. 175 : 105456. https:// doi.org/10.1016/j.compag.2020.105456

10.1016/j.compag.2020.105456

Wang, B., Y. Gao, X. Yuan, S. Xiong, and X. Feng. 2020. From species to cultivar: Soybean cultivar recognition using joint leaf image patterns by multiscale sliding chord matching. Biosyst. Eng. 194 : 99-111. https://doi.org/10.1016/j.biosystemseng.2020.03.019

10.1016/j.biosystemseng.2020.03.019

Yamaguchi, T., Y. Tanaka, Y. Imachi, M. Yamashita, and K. Katsura. 2021. Feasibility of combining deep learning and rgb images obtained by unmanned aerial vehicle for leaf area index estimation in rice. Remote Sens. 13 : 84.

10.3390/rs13010084

Yan, Y., B. Ni, H. Wei, and X. Yang. 2020. Fine-grained image analysis via progressive feature learning. Neurocomputing 396 : 254-265. https://doi.org/10.1016/j.neucom.2018.07.100

10.1016/j.neucom.2018.07.100

Yang, K., W. Zhong, and F. Li. 2020. Leaf segmentation and classification with a complicated background using deep learning. Agronomy 10 : 1721.

10.3390/agronomy10111721

Yigit, E., K. Sabanci, A. Toktas, and A. Kayabasi. 2019. A study on visual features of leaves in plant identification using artificial intelligence techniques. Comput. Electron. Agric. 156 : 369-377. https://doi.org/10.1016/j.compag.2018.11.036

10.1016/j.compag.2018.11.036

Information

Publisher :The Korean Society of Crop Science
Publisher(Ko) :한국작물학회
Journal Title :The Korean Journal of Crop Science
Journal Title(Ko) :한국작물학회지
Volume : 70
No :2
Pages :68-78
Received Date : 2025-02-03
Revised Date : 2025-03-20
Accepted Date : 2025-03-26
DOI :https://doi.org/10.7740/kjcs.2025.70.2.068

The Korean Journal of Crop Science ISSN:0252-9777(Print) 2287-8432(Online) 한국작물학회지

All Issue