Citrus Diseases Detection & Classification using DL and ML Models: A Systematic Review
Keywords:
Citrus Diseases; Deep Learning; Machine Learning; Disease Detection; Disease Classification; Convolutional Neural Networks; YOLO; Transfer Learning; Computer VisionAbstract
Citrus diseases are a major challenge in agricultural production because they can reduce crop yield, fruit quality, and farmers’ economic returns. Early and accurate detection of diseases is therefore essential for effective crop management and sustainable citrus production. Traditional disease identification methods mainly depend on visual inspection and expert knowledge, which can be time-consuming, subjective, and difficult to apply on a large scale. This systematic review examines the application of Deep Learning (DL) and Machine Learning (ML) models for citrus disease detection and classification. The review analyses recent studies focusing on image processing, conventional machine learning algorithms, Convolutional Neural Networks (CNNs), transfer learning, YOLO-based object detection, attention mechanisms, ensemble learning, and Vision Transformers. It compares commonly used datasets, preprocessing techniques, model architectures, evaluation metrics, and reported classification or detection performance. The findings indicate that DL models generally provide higher accuracy and stronger feature-learning capabilities than traditional ML approaches, while lightweight and YOLO-based models offer greater potential for real-time agricultural applications. However, challenges remain concerning limited and imbalanced datasets, complex field backgrounds, variations in lighting and disease symptoms, early-stage disease identification, computational requirements, and model generalisation across different citrus varieties and geographical locations. The review identifies these research gaps and highlights future opportunities for developing robust, lightweight, explainable, and field-deployable AI systems for automated citrus disease detection and classification.
References
Liu, Z., Xiang, X., Qin, J., Ma, Y., Zhang, Q., and Xiong, N. N. (2022) “Image recognition of Dai, Q., Xiao, Y., Lv, S., Song, S., Xue, X., Liang, S., Huang, Y., & Li, Z. (2024). YOLOv8-GABNet: An enhanced lightweight network for the high-precision recognition of citrus diseases and nutrient deficiencies. Agriculture, 14(11), 1964. https://doi.org/10.3390/agriculture14111964 MDPI
Goyal, A., & Lakhwani, K. (2025). Integrating advanced deep learning techniques for enhanced detection and classification of citrus leaf and fruit diseases. Scientific Reports, 15, 12659. https://doi.org/10.1038/s41598-025-97159-0 Nature
Injante, R., & Sánchez-Isuiza, S. (2025). Detection of citrus diseases using artificial intelligence: A systematic review. LatIA, 3, 122. https://doi.org/10.62486/latia2025122 DOI
Dai, Q., Xiao, Y., Lv, S., Song, S., Xue, X., Liang, S., Huang, Y., & Li, Z. (2024). YOLOv8-GABNet: An enhanced lightweight network for the high-precision recognition of citrus diseases and nutrient deficiencies. Agriculture, 14(11), 1964. https://doi.org/10.3390/agriculture14111964
Butt, N., Iqbal, M. M., Ramzan, S., Raza, A., Abualigah, L., Fitriyani, N. L., Gu, Y., & Syafrudin, M. (2025). Citrus diseases detection using innovative deep learning approach and hybrid meta-heuristic. PLOS ONE, 20(1), e0316081. https://doi.org/10.1371/journal.pone.0316081
Kujur, L., Gupta, V., & Singhal, A. (2025). A hybrid multi-optimizer approach using CNN and GB for accurate prediction of citrus fruit diseases. Discover Applied Sciences, 7, 151. https://doi.org/10.1007/s42452-025-06593-2
Zhu, H., Wang, D., Wei, Y., Wang, P., & Su, M. (2025). YOLOV8-CMS: A high-accuracy deep learning model for automated citrus leaf disease classification and grading. Plant Methods, 21, 88. https://doi.org/10.1186/s13007-025-01396-3
Sireesha, N. V., Rekha, G., & Almenweer, R. A. (2025). Unassailable citrus disease classification via multi-stage deep ensemble learning with vision transformers. Scientific Reports, 15, 40573. https://doi.org/10.1038/s41598-025-24416-7
Feng, W., Liu, J., Li, Z., & Lyu, S. (2025). YOLO-Citrus: A lightweight and efficient model for citrus leaf disease detection in complex agricultural environments. Frontiers in Plant Science, 16, 1668036. https://doi.org/10.3389/fpls.2025.1668036
Mo, H., & Wei, L. (2024). Lightweight citrus leaf disease detection model based on ARMS and cross-domain dynamic attention. Journal of King Saud University—Computer and Information Sciences, 36(7), 102133. https://doi.org/10.1016/j.jksuci.2024.102133 Classifying adaxial and abaxial sides of diseased citrus leaves with selected hyperspectral bands and YOLOv8. (2024). Smart Agricultural Technology, 9, 100600. https://doi.org/10.1016/j.atech.2024.100600 ScienceDirect
Xue, R., & Wang, L. (2025). Research on lightweight citrus leaf pest and disease detection based on PEW-YOLO. Processes, 13(5), 1365. https://doi.org/10.3390/pr13051365 MDPI
Citrus disease detection based on dilated reparam feature enhancement and shared parameter head. (2025). Sensors, 25(7), 1971. https://doi.org/10.3390/s25071971 DOI
CBACA-YOLOv5: A symmetric and asymmetric attention-driven detection framework for citrus leaf disease identification. (2025). Symmetry, 17(4), 617. https://doi.org/10.3390/sym17040617 MDPI
Multi-component image analysis for citrus disease detection using convolutional neural networks. (2025). Crop Protection, 193, 107181. https://doi.org/10.1016/j.cropro.2025.107181 ScienceDirect
Wang, S., Zhang, Y., Li, R., et al. (2023). Detection of citrus diseases in complex backgrounds based on image–text multimodal fusion and knowledge assistance. Frontiers in Plant Science. https://doi.org/10.3389/fpls.2023.1280365
Mazzia, V., Comba, L., Khaliq, A., Chiaberge, M., & Gay, P. (2023). Image acquisition, preprocessing and classification of citrus fruit diseases: A systematic literature review. Sustainability, 15(12), 9643. https://doi.org/10.3390/su15129643
Karthik, R., Hussain, S., George, T. T., & Mishra, R. (2023). A dual track deep fusion network for citrus disease classification using group shuffle depthwise feature pyramid and Swin Transformer. Ecological Informatics, 78, 102302. https://doi.org/10.1016/j.ecoinf.2023.102302 DOI
Tang, Y., Yang, J., Zhuang, J., Hou, C., Miao, A., Ren, J., et al. (2023). Early detection of citrus anthracnose caused by Colletotrichum gloeosporioides using hyperspectral imaging. Computers and Electronics in Agriculture, 214, 108348. https://doi.org/10.1016/j.compag.2023.108348 DOI
Mohammed, E. A., & Mohammed, G. H. (2023). Citrus leaves disease diagnosis. Indonesian Journal of Electrical Engineering and Computer Science, 31(2), 925–932. https://doi.org/10.11591/ijeecs.v31.i2.pp925-932 DOI
Peng, K., Ma, W., Lu, J., Tian, Z., & Yang, Z. (2023). Application of machine vision technology in citrus production. Applied Sciences, 13(16), 9334. https://doi.org/10.3390/app13169334 DOI
Faisal, S., Javed, K., Ali, S., Alasiry, A., Marzougui, M., Khan, M. A., et al. (2023). Deep transfer learning based detection and classification of citrus plant diseases. Computers, Materials & Continua, 76(1), 895–914. https://doi.org/10.32604/cmc.2023.039781 DOI
Dou, S., Wang, L., Fan, D., Miao, L., Yan, J., & He, H. (2023). Classification of citrus Huanglongbing degree based on CBAM-MobileNetV2 and transfer learning. Sensors, 23(12), 5587. https://doi.org/10.3390/s23125587 DOI
Dhiman, P., Kaur, A., Hamid, Y., Alabdulkreem, E., Elmannai, H., & Ababneh, N. (2023). Smart disease detection system for citrus fruits using deep learning with edge computing. Sustainability, 15(5), 4576. https://doi.org/10.3390/su15054576 DOI
Firdaus, M. H., Utami, E., & Ariatmanto, D. (2023). Detection and classification of citrus diseases based on a combination of features using the DenseNet-169 model. Sinkron, 8(4), 2592–2601. https://doi.org/10.33395/sinkron.v8i4.12974
Liu, Z., Xiang, X., Qin, J., Tan, Y., Zhang, Q., & Xiong, N. N. (2021). Image recognition of citrus diseases based on deep learning. Computers, Materials & Continua, 66(1), 457–466. https://doi.org/10.32604/cmc.2020.012165 Tech Science
Dananjayan, S., Tang, Y., Zhuang, J., Hou, C., & Luo, S. (2022). Assessment of state-of-the-art deep learning based citrus disease detection techniques using annotated optical leaf images. Computers and Electronics in Agriculture, 193, 106658. https://doi.org/10.1016/j.compag.2021.106658 ScienceDirect
Zhang, X., Xun, Y., & Chen, Y. (2022). Automated identification of citrus diseases in orchards using deep learning. Biosystems Engineering, 223, 249–258. https://doi.org/10.1016/j.biosystemseng.2022.09.006 ScienceDirect
Ding, Y., et al. (2022). An automatic identification system for citrus greening disease (Huanglongbing) using a YOLO convolutional neural network. Frontiers in Plant Science, 13, 1002606. https://doi.org/10.3389/fpls.2022.1002606 Frontiers
He, C., Li, X., Liu, Y., Yang, B., Wu, Z., Tan, S., Ye, D., & Weng, H. (2022). Combining multicolor fluorescence imaging with multispectral reflectance imaging for rapid citrus Huanglongbing detection based on lightweight convolutional neural network using a handheld device. Computers and Electronics in Agriculture, 194, 106808. https://doi.org/10.1016/j.compag.2022.106808 ScienceDirect
Frederick, Q., Qin, J., & Kim, M. (2022). Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data. Frontiers in Plant Science, 13, 1043712. https://doi.org/10.3389/fpls.2022.1043712 Frontiers
Senthilkumar, C., et al. (2021). An effective citrus disease detection and classification using deep learning based Inception ResNet V2 model. Turkish Journal of Computer and Mathematics Education, 12(12), 2283–2296. https://doi.org/10.17762/turcomat.v12i12.7809 Turcomat
Gumaei, A., et al. (2021). Automatic detection of citrus fruit and leaves diseases using deep neural network model. IEEE Access, 9, 112942–112954. https://doi.org/10.1109/ACCESS.2021.3096895 DOAJ
Smartphone assist deep neural network to detect the citrus diseases in Agri-informatics. (2022). Global Transitions Proceedings, 3(2), 392–398. https://doi.org/10.1016/j.gltp.2021.10.004 ScienceDirect
Citrus disease detection and classification using based on convolution deep neural network. (2022). Microprocessors and Microsystems, 95, 104687. https://doi.org/10.1016/j.micpro.2022.104687 ScienceDirect
Detection of citrus black spot disease and ripeness level in orange fruit using learning-to-augment incorporated deep networks. (2022). Ecological Informatics, 71, 101829. https://doi.org/10.1016/j.ecoinf.2022.101829 ScienceDirect
Yang, S., Li, C., Li, X., Jiang, J., Zhao, Y., Wang, X., Chen, W., Liu, R., & Xu, K. (2024). Early detection of fungal infection in citrus using biospeckle imaging. Computers and Electronics in Agriculture, 225, 109293. https://doi.org/10.1016/j.compag.2024.109293 ScienceDirect
Dhiman, P., Kaur, A., Hamid, Y., Alabdulkreem, E., Elmannai, H., & Ababneh, N. (2023). Smart disease detection system for citrus fruits using deep learning with edge computing. Sustainability, 15(5), 4576. https://doi.org/10.3390/su15054576 DOI
Tang, Y., Yang, J., Zhuang, J., Hou, C., Miao, A., Ren, J., et al. (2023). Early detection of citrus anthracnose caused by Colletotrichum gloeosporioides using hyperspectral imaging. Computers and Electronics in Agriculture, 214, 108348. https://doi.org/10.1016/j.compag.2023.108348
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
