Intelligent detection system of diseases in hydroponic crops using artificial vision
DOI:
https://doi.org/10.37431/conectividad.v7i1.339Keywords:
Computer vision, MobileNetV2, Transfer learning, Disease detection, Hydroponic cropsAbstract
This work proposes the development of an intelligent system for early disease detection in hydroponic lettuce crops using computer vision and artificial intelligence (AI). A model based on the MobileNetV2 architecture was implemented, it was trained using transfer learning and executed on a Raspberry Pi 4 to ensure portability and low resource consumption. The training stage was with a set of 2,180 images classified into four classes (healthy, mildew, powdery mildew, and bacterial spot), using data augmentation and preprocessing techniques tailored to the model. An accuracy of 96.34% was achieved in the validation set and 93.64% in the test set, demonstrating high generalization capabilities. The model was integrated into a prototype that captures images online, performs local inferences, and provides immediate visual physical feedback about the detected disease. This research demonstrates the technical feasibility of applying AI to precision agriculture for hydroponic environments, reducing manual intervention and improving production efficiency, with the potential to scale to smart agricultural solutions.
References
Ahmed, S., Hasan, M. M., Ahmed, T., Sony, M. R. K., & Kabir, M. H. (2022). Less is more: Lighter and faster deep neural architecture for tomato leaf disease classification. IEEE Access, 10, 68868–68884. https://doi.org/10.1109/ACCESS.2022.3187203 DOI: https://doi.org/10.1109/ACCESS.2022.3187203
Akkem, Y., Biswas, S. K., & Varanasi, A. (2023). Smart farming using artificial intelligence: A review. Engineering Applications of Artificial Intelligence, 120, 105899. https://doi.org/10.1016/J.ENGAPPAI.2023.105899 DOI: https://doi.org/10.1016/j.engappai.2023.105899
Bhandari, N., Agarwal, R., & Bhandari, N. (2024). An insight on artificial intelligence (AI) and Internet of Things (IoT) driven hydroponics farming. E3S Web of Conferences, 556, 01036. https://doi.org/10.1051/e3sconf/202455601036 DOI: https://doi.org/10.1051/e3sconf/202455601036
Chiu, V., Ma, T., Jin, K., Li, Z., Sun, Y., Lee, J., Liu, D., Krouse, E., Chen, Y., & Li, B. (2020). Agriculture-Vision: A large aerial image database for agricultural pattern analysis. En Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 59-60). IEEE. DOI: https://doi.org/10.1109/CVPR42600.2020.00290
Duhan, S., Gulia, P., Gill, N. S., & Narwal, E. (2025). RTR_Lite_MobileNetV2: A lightweight and efficient model for plant disease detection and classification. Current Plant Biology, 42(3), 100459. https://doi.org/10.1016/j.cpb.2025.100459 DOI: https://doi.org/10.1016/j.cpb.2025.100459
Gowtham, V., Guhan, N. S., Balasubramanian, M., & Gangadurai, E. (2024). A smart hydroponic plant disease detection system using CNN. International Journal of Electronics and Communication Engineering, 7(2), 1–14.
Jeyabose, A., Eunice, J., Popescu, D. E., Chowdary, M. K., & Hemanth, J. (2022). Deep learning-based leaf disease detection in crops using images for agricultural applications. Agronomy, 12(10), 2395. https://doi.org/10.3390/agronomy12102395 DOI: https://doi.org/10.3390/agronomy12102395
Kamilaris, A., & Prenafeta-Boldú, F. X. (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 DOI: https://doi.org/10.1016/j.compag.2018.02.016
Khan, A., & Singh, A. (2024). Comparative analysis of image annotation tools: LabelImg, VGG Annotator, Label Studio, and Roboflow. JETIR Research Journal.
Li, Y., Chen, J., Li, Z., Sun, Q., & Pan, M. (2023). Hydroponic lettuce defective leaves identification based on improved YOLOv5s. Frontiers in Plant Science, 14, 1242337. https://doi.org/10.3389/fpls.2023.1242337 DOI: https://doi.org/10.3389/fpls.2023.1242337
Lu, Y., Zhang, Y., Wang, Y., & Li, X. (2023). Improved MobileNetV2 crop disease identification model for intelligent agriculture. PeerJ Computer Science, 9, e1595. https://doi.org/10.7717/peerj-cs.1595 DOI: https://doi.org/10.7717/peerj-cs.1595
Musa, A., Hamada, M., Aliyu, F. M., & Hassan, M. (2021). An intelligent plant disease detection system for smart hydroponic using convolutional neural network. En Proceedings of the 2021 IEEE 14th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) (pp. 345–351). IEEE. https://doi.org/10.1109/MCSoC51149.2021.00058 DOI: https://doi.org/10.1109/MCSoC51149.2021.00058
Rahman, M. A., Chakraborty, N. R., Sufiun, A., Banshal, S. K., & Tajnin, F. R. (2024). An AIoT-based hydroponic system for crop recommendation and nutrient parameter monitorization. Smart Agricultural Technology, 8, 100472. https://doi.org/10.1016/j.atech.2024.100472 DOI: https://doi.org/10.1016/j.atech.2024.100472
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. En Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4510–4520). IEEE. https://doi.org/10.1109/CVPR.2018.00474 DOI: https://doi.org/10.1109/CVPR.2018.00474
Swarup Sahoo, R., Kumar Tripathy, C., Samantasinghar, U., & Biswal, P. (2022). Implementation of an indoor deep water culture farming system using IoT. En 2022 IEEE 2nd International Symposium on Sustainable Energy, Signal Processing and Cyber Security (iSSSC) (pp. 1–5). IEEE. https://doi.org/10.1109/iSSSC56467.2022.10051358 DOI: https://doi.org/10.1109/iSSSC56467.2022.10051358
Ye, M., Ward, P. J., De Plaen, J. J-F. G., & Koks, E. E. (2025). A deep learning pipeline to power infrastructure detection in high-resolution satellite images. Big Earth Data. https://doi.org/10.1080/20964471.2025.2490408 DOI: https://doi.org/10.1080/20964471.2025.2490408
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Instituto Superior Tecnológico Universitario Rumiñahui
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The originals published in the electronic edition under the first publication rights of the journal belong to the Instituto Superior Tecnológico Universitario Rumiñahui; therefore, it is necessary to cite the source in any partial or total reproduction. All the contents of the electronic journal are distributed under a Creative Commons Attribution-Noncommercial 4.0 International (CC-BY-NC 4.0) license.
2.png){kind=logo}
