Detección automática de enfermedades foliares del cafeto mediante reconocimiento de patrones

John C. Santa-María; Ciro Rodriguez

doi:10.51252/rcsi.v6i1.1349

Autores/as

John C. Santa-María Universidad Nacional Mayor de San Marcos - Universidad Nacional de San Martín https://orcid.org/0000-0002-8594-4865
Ciro Rodríguez Universidad Nacional Mayor de San Marcos https://orcid.org/0000-0003-2112-1349

DOI:

https://doi.org/10.51252/rcsi.v6i1.1349

Palabras clave:

transferencia de conocimiento, clasificación supervisada, métricas de desempeño, validación diagnóstica, visión artificial

Resumen

La detección temprana de enfermedades foliares del cafeto es clave para reducir pérdidas productivas; sin embargo, el diagnóstico visual en campo presenta limitaciones asociadas a la subjetividad y la variabilidad ambiental. El objetivo de este estudio fue diseñar y evaluar un modelo híbrido de reconocimiento de patrones para clasificar hojas de cafeto sanas, con roya y con ojo de gallo a partir de imágenes capturadas en condiciones reales en Saposoa (San Martín, Perú). Se empleó un conjunto de datos propio de 1 500 imágenes validadas por especialista (500 por clase), ampliado mediante aumento de datos controlado hasta 6 000 imágenes balanceadas. ResNet18 fue utilizado como extractor de características por transferencia de aprendizaje y se compararon tres clasificadores supervisados: SVM, Random Forest y XGBoost. La evaluación se realizó mediante validación cruzada estratificada de 10 pliegues y un conjunto de prueba independiente (20%). El modelo ResNet18 + SVM obtuvo el mejor desempeño, con una accuracy de 0.9742, F1-macro de 0.9730 y AUC-macro de 0.9968, superando a Random Forest (accuracy = 0.9367) y XGBoost (accuracy = 0.9583). El análisis inferencial mediante ANOVA y la prueba de Tukey HSD confirmó diferencias estadísticamente significativas entre modelos (p < 0.001). Los resultados evidencian la robustez y viabilidad del enfoque propuesto para apoyar el diagnóstico fitosanitario del cafeto en condiciones reales de campo.

Descargas

Los datos de descargas todavía no están disponibles.

Biografía del autor/a

Ciro Rodríguez, Universidad Nacional Mayor de San Marcos

The project proposes the design and evaluation of a hybrid automatic analysis model to identify and classify diseases in coffee leaves, specifically rust (Hemileia vastatrix) and eye spot (Mycena citricolor), which severely impact the productivity and economic stability of small producers in the San Martín region. A proprietary dataset of 4,000 digital images of healthy and diseased leaves will be created, captured in the field under a standardized protocol and labeled by plant health specialists. The images will be processed through computer vision and transfer learning using ResNet50 as a feature extractor, whose representations will feed supervised classifiers such as SVM, Random Forest, and XGBoost. The performance of the hybrid model will be evaluated using metrics such as accuracy, sensitivity, specificity, and F1-score, comparing its results against expert diagnoses, with the aim of providing an objective, reproducible, and applicable tool for the phytosanitary monitoring of coffee crops.

Citas

Abade, A. S., Ferreira, P. A., & Vidal, F. de B. (2020). Plant Diseases recognition on images using Convolutional Neural Networks: A Systematic Review. Cornell University. https://doi.org/https://doi.org/10.48550/arXiv.2009.04365

Abdullah, H. M., Mohana, N. T., Khan, B. M., Ahmed, S. M., Hossain, M., Islam, K. S., Redoy, M. H., Ferdush, J., Bhuiyan, M. A. H. B., Hossain, M. M., & Ahamed, T. (2023). Present and future scopes and challenges of plant pest and disease (P&D) monitoring: Remote sensing, image processing, and artificial intelligence perspectives. Remote Sensing Applications: Society and Environment, 32, 100996. https://doi.org/10.1016/j.rsase.2023.100996

Abuhayi, B. M., & Mossa, A. A. (2023). Coffee disease classification using Convolutional Neural Network based on feature concatenation. Informatics in Medicine Unlocked, 39, 101245. https://doi.org/10.1016/j.imu.2023.101245

Adelaja, O., & Pranggono, B. (2025). Leveraging Deep Learning for Real-Time Coffee Leaf Disease Identification. AgriEngineering, 7(1), 13. https://doi.org/10.3390/agriengineering7010013

Archana, R., & Jeevaraj, P. S. E. (2024). Deep learning models for digital image processing: a review. Artificial Intelligence Review, 57(1), 11. https://doi.org/10.1007/s10462-023-10631-z

Arif, A., Putrawansyah, F., & Jangcik, I. (2025). Detection of Coffee Leaf Diseases Using Lightweight Deep Learning: A Comparative Study of EfficientNet-B0 and Vision Transformer. Ingénierie Des Systèmes d Information, 30(9), 2393–2404. https://doi.org/10.18280/isi.300915

Atila, Ü., Uçar, M., Akyol, K., & Uçar, E. (2021). Plant leaf disease classification using EfficientNet deep learning model. Ecological Informatics, 61, 101182. https://doi.org/10.1016/j.ecoinf.2020.101182

Aufar, Y., & Kaloka, T. P. (2022). Robusta coffee leaf diseases detection based on MobileNetV2 model. International Journal of Electrical and Computer Engineering (IJECE), 12(6), 6675. https://doi.org/10.11591/ijece.v12i6.pp6675-6683

Avelino, J., Cristancho, M., Georgiou, S., Imbach, P., Aguilar, L., Bornemann, G., Läderach, P., Anzueto, F., Hruska, A. J., & Morales, C. (2015). The coffee rust crises in Colombia and Central America (2008–2013): impacts, plausible causes and proposed solutions. Food Security, 7(2), 303–321. https://doi.org/10.1007/s12571-015-0446-9

Ayikpa, K. J., Ayikpa, K. J., Ayikpa, K. J., Mamadou, D., Gouton, P., & Adou, K. J. (2022). Experimental Evaluation of Coffee Leaf Disease Classification and Recognition Based on Machine Learning and Deep Learning Algorithms. Journal of Computer Science, 18(12), 1201–1212. https://doi.org/10.3844/jcssp.2022.1201.1212

Chavarro, A. F., Renza, D., & Ballesteros, D. M. (2023). Influence of Hyperparameters in Deep Learning Models for Coffee Rust Detection. Applied Sciences, 13(7), 4565. https://doi.org/10.3390/app13074565

Ehrenbergerová, L., Kučera, A., Cienciala, E., Trochta, J., & Volařík, D. (2018). Identifying key factors affecting coffee leaf rust incidence in agroforestry plantations in Peru. Agroforestry Systems, 92(6), 1551–1565. https://doi.org/10.1007/s10457-017-0101-x

Fragoso, J., Silva, C., Paixão, T., Alvarez, A. B., Júnior, O. C., Florez, R., Palomino-Quispe, F., Savian, L. G., & Trazzi, P. A. (2025). Coffee-Leaf Diseases and Pests Detection Based on YOLO Models. Applied Sciences, 15(9), 5040. https://doi.org/10.3390/app15095040

Julca-Otiniano, A., Alvarado-Huamán, L., Castro-Cepero, V., Borjas-Ventura, R., Gómez-Pando, L., Pereira, A. P., Nielen, S., Ingelbrecht, I., Silva, M. do C., & Várzea, V. (2024). New Races of Hemileia vastatrix Detected in Peruvian Coffee Fields. Agronomy, 14(8), 1811. https://doi.org/10.3390/agronomy14081811

Mansouri, N., Guessmi, H., & Alkhalil, A. (2024). A deep learning model for detection and classification of coffee-leaf diseases using the transfer-learning technique. International Journal of Advances in Intelligent Informatics, 10(3), 379. https://doi.org/10.26555/ijain.v10i3.1573

Martinez, F., Montiel, H., & Martinez, F. (2022). A Machine Learning Model for the Diagnosis of Coffee Diseases. International Journal of Advanced Computer Science and Applications, 13(4). https://doi.org/10.14569/IJACSA.2022.01304110

Novtahaning, D., Shah, H. A., & Kang, J.-M. (2022). Deep Learning Ensemble-Based Automated and High-Performing Recognition of Coffee Leaf Disease. Agriculture, 12(11), 1909. https://doi.org/10.3390/agriculture12111909

Pham, T. C., Nguyen, V. D., Le, C. H., Packianather, M., & Hoang, V.-D. (2023). Artificial intelligence-based solutions for coffee leaf disease classification. IOP Conference Series: Earth and Environmental Science, 1278(1), 012004. https://doi.org/10.1088/1755-1315/1278/1/012004

Poma-Angamarca, R. A., Rojas, J. R., Sánchez-Rodríguez, A., & Ruiz-González, M. X. (2024). Diversity of Leaf Fungal Endophytes from Two Coffea arabica Varieties and Antagonism towards Coffee Leaf Rust. Plants, 13(6), 814. https://doi.org/10.3390/plants13060814

Saavedra-Ramírez, J. (2023). Impacto social de los Proyectos de Extensión Agraria durante el 2005 al 2010 en San Martín y Amazonas, Perú. Revista Amazónica de Ciencias Económicas, 2(1), e433. https://doi.org/10.51252/race.v2i1.433

Siddiqua, A., Kabir, M. A., Ferdous, T., Ali, I. B., & Weston, L. A. (2022). Evaluating Plant Disease Detection Mobile Applications: Quality and Limitations. Agronomy, 12(8), 1869. https://doi.org/10.3390/agronomy12081869