Aplicación de aprendizaje profundo en la detección fitosanitaria del cacao usando visión por computadora

Autores/as

  • Jorge Raul Navarro-Cabrera Universidad de Huánuco
  • José Guillermo Beraún-Barrantes Universidad de Huánuco
  • Ángel Cárdenas-García Universidad Nacional de San Martín https://orcid.org/0000-0001-7524-1421
  • Carlos Mauricio Lozano-Carranza TUSAN Ingenieros Consultores

DOI:

https://doi.org/10.51252/rcsi.v6i1.1385

Palabras clave:

aprendizaje profundo, diagnóstico automatizado, modelos de clasificación, sanidad vegetal, visión artificial

Resumen

Este estudio analizó la aplicación del aprendizaje profundo en la detección fitosanitaria automatizada del cacao mediante visión por computadora, comparando el desempeño de tres arquitecturas: ResNet50, EfficientNet-B0 y Vision Transformer (ViT-B/16). Se implementó un pipeline reproducible que integró preprocesamiento de imágenes, validación cruzada estratificada de cinco pliegues y análisis estadístico inferencial mediante ANOVA de medidas repetidas. El conjunto de datos estuvo conformado por 4 390 imágenes RGB de frutos de cacao, distribuidas en tres clases desbalanceadas: Healthy, Black Pod Rot y Pod Borer. Todos los modelos fueron ajustados mediante fine-tuning completo y entrenados con el optimizador AdamW, parada temprana y programación dinámica de la tasa de aprendizaje. Los resultados mostraron valores medios de F1 macro superiores a 0.96 en las tres arquitecturas, sin diferencias estadísticamente significativas entre modelos (F = 0.278, p = 0.7645). Las curvas de entrenamiento evidenciaron convergencia estable y baja variabilidad inter-fold, sin indicios de sobreajuste. Los hallazgos indican que el rendimiento depende principalmente de la calidad del pipeline experimental y del manejo del desbalance de clases, más que del tipo de arquitectura empleada.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Anjali, Jena, A., Bamola, A., Mishra, S., Jain, I., Pathak, N., Sharma, N., Joshi, N., Pandey, R., Kaparwal, S., Yadav, V., Gupta, A. K., Jha, A. K., Bhatt, S., Kumar, V., Naik, B., Rustagi, S., Preet, M. S., & Akhtar, S. (2024). State-of-the-art non-destructive approaches for maturity index determination in fruits and vegetables: principles, applications, and future directions. Food Production, Processing and Nutrition, 6(1), 56. https://doi.org/10.1186/s43014-023-00205-5

Bono, A., Guaragnella, C., & D’Orazio, T. (2026). A perspective analysis of imaging-based monitoring systems in precision viticulture: Technologies, intelligent data analyses and research challenges. Artificial Intelligence in Agriculture, 16(1), 62–84. https://doi.org/10.1016/j.aiia.2025.08.001

Charry, A., Perea, C., Ramírez, K., Zambrano, G., Yovera, F., Santos, A., Jiménez, T., Romero, M., Lundy, M., Quintero, M., & Pulleman, M. (2025). The bittersweet economics of different cacao production systems in Colombia, Ecuador and Peru. Agricultural Systems, 224, 104235. https://doi.org/10.1016/j.agsy.2024.104235

Cilas, C., & Bastide, P. (2020). Challenges to Cocoa Production in the Face of Climate Change and the Spread of Pests and Diseases. Agronomy, 10(9), 1232. https://doi.org/10.3390/agronomy10091232

Deepa, R., Varun, P., Shoba, L. K., Swathy, R., & Prabhu, B. (2025). Advanced Image Processing Techniques for Precision Agriculture. In Innovations and Developments in Unmanned Aerial Vehicles (pp. 227–244). IGI Global Scientific Publishing. https://doi.org/10.4018/979-8-3693-8462-6.ch010

Delgado-Ospina, J., Molina-Hernández, J. B., Chaves-López, C., Romanazzi, G., & Paparella, A. (2021). The Role of Fungi in the Cocoa Production Chain and the Challenge of Climate Change. Journal of Fungi, 7(3), 202. https://doi.org/10.3390/jof7030202

He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. In Cornell University. https://doi.org/https://doi.org/1512.03385

Injante, R., Rios-Trigoso, G., Ramírez-Shupingahua, S., & Tejada Shupingahua, K. (2025). Procesamiento de imágenes para la detección de la madurez del fruto: una revisión sistemática. Revista Peruana de Ingeniería, Arquitectura y Medio Ambiente, 2(1). https://doi.org/10.37711/repiama.2025.2.1.3

Kingma, J., & Ba, D. P. (2014). Adam: A Method for Stochastic Optimization. Cornell University. https://doi.org/https://doi.org/10.48550/arXiv.1412.6980

Lebrini, Y., & Ayerdi Gotor, A. (2024). Crops Disease Detection, from Leaves to Field: What We Can Expect from Artificial Intelligence. Agronomy, 14(11), 2719. https://doi.org/10.3390/agronomy14112719

Magfirah, N., Sartiami, D., Niogret, J., & Ekayanti, A. (2025). Biological parameter of cocoa pod borer Conopomorpha cramerella (Lepidoptera: Gracillariidae) under laboratory conditions. IOP Conference Series: Earth and Environmental Science, 1494(1), 012020. https://doi.org/10.1088/1755-1315/1494/1/012020

Mall, P. K., Singh, P. K., Srivastav, S., Narayan, V., Paprzycki, M., Jaworska, T., & Ganzha, M. (2023). A comprehensive review of deep neural networks for medical image processing: Recent developments and future opportunities. Healthcare Analytics, 4, 100216. https://doi.org/10.1016/j.health.2023.100216

Miyittah, M. K., Kosivi, R. K., Tulashie, S. K., Addi, M. N., & Tawiah, J. Y. (2022). The need for alternative pest management methods to mitigate risks among cocoa farmers in the Volta region, Ghana. Heliyon, 8(12), e12591. https://doi.org/10.1016/j.heliyon.2022.e12591

Paparella, A., Schirone, M., & López, C. C. (2025). The Health Impact of Cocoa from Cultivation to the Formation of Biogenic Amines: An Updated Review. Foods, 14(2), 255. https://doi.org/10.3390/foods14020255

Polania Bello, V. (2023). Diagnosis of the agronomic and phytosanitary management practices of cocoa producers in San José del Fragua: the case of the Cerafín Garcia property. Environmental Research and Ecotoxicity, 2, 55. https://doi.org/10.56294/ere202355

Puig, A. S., Irish, B., Ayala-Silva, T., Wurzel, S., & Gutierrez, O. (2022). Effect of Cacao Black Pod Rot Screening Method on Disease Reaction Determination. The 1st International Online Conference on Agriculture—Advances in Agricultural Science and Technology, 71. https://doi.org/10.3390/IOCAG2022-12215

Quintero, I., Ceccaldi, A., Martínez, H., Santander, M., Rodríguez, J., & Escobar, S. (2025). Dry cacao pulp in chocolate bars: A sustainable, nutrient-rich sweetener with enhanced sensory quality through refractance windows drying. Applied Food Research, 5(1), 100700. https://doi.org/10.1016/j.afres.2025.100700

Raj, M., & Prahadeeswaran, M. (2025). Revolutionizing agriculture: a review of smart farming technologies for a sustainable future. Discover Applied Sciences, 7(9), 937. https://doi.org/10.1007/s42452-025-07561-6

Ray, R. K., Chakravarty, S., Dash, S., Ghosh, A., Mohanty, S. N., Reddy Chirra, V. R., Ayouni, S., & Khan, M. I. (2025). Precision pest management in agriculture using Inception V3 and EfficientNet B4: A deep learning approach for crop protection. Information Processing in Agriculture. https://doi.org/10.1016/j.inpa.2025.09.005

Schmidt, J. E., Puig, A. S., DuVal, A. E., & Pfeufer, E. E. (2023). Phyllosphere microbial diversity and specific taxa mediate within-cultivar resistance to Phytophthora palmivora in cacao. MSphere, 8(5). https://doi.org/10.1128/msphere.00013-23

Shafay, M., Hassan, T., Owais, M., Hussain, I., Khawaja, S. G., Seneviratne, L., & Werghi, N. (2025). Recent advances in plant disease detection: challenges and opportunities. Plant Methods, 21(1), 140. https://doi.org/10.1186/s13007-025-01450-0

Song, X., Yan, L., Liu, S., Gao, T., Han, L., Jiang, X., Jin, H., & Zhu, Y. (2025). Agricultural Image Processing: Challenges, Advances, and Future Trends. Applied Sciences, 15(16), 9206. https://doi.org/10.3390/app15169206

Taha, M. F., Mao, H., Zhang, Z., Elmasry, G., Awad, M. A., Abdalla, A., Mousa, S., Elwakeel, A. E., & Elsherbiny, O. (2025). Emerging Technologies for Precision Crop Management Towards Agriculture 5.0: A Comprehensive Overview. Agriculture, 15(6), 582. https://doi.org/10.3390/agriculture15060582

Tan, M., & Le, Q. V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Cornell University. https://doi.org/https://doi.org/10.48550/arXiv.1905.11946

Villalobos-Culqui, C., Valles-Coral, M. A., García-Rivas-Plata, C., & Tuesta-Hidalgo, O. A. (2025). Modelo de visión artificial basada en redes neuronales convolucionales para identificación de mazorca negra en plantaciones de cacao. Revista Científica de Sistemas e Informática, 5(1), e678. https://doi.org/10.51252/rcsi.v5i1.678

Vinci, G., Ruggeri, M., Gobbi, L., & Savastano, M. (2024). Social Life Cycle Assessment of Cocoa Production: Evidence from Ivory Coast and Ghana. Resources, 13(10), 141. https://doi.org/10.3390/resources13100141

Wang, Y., Deng, Y., Zheng, Y., Chattopadhyay, P., & Wang, L. (2025). Vision Transformers for Image Classification: A Comparative Survey. Technologies, 13(1), 32. https://doi.org/10.3390/technologies13010032

Waqas, M., Naseem, A., Humphries, U. W., Hlaing, P. T., Dechpichai, P., & Wangwongchai, A. (2025). Applications of machine learning and deep learning in agriculture: A comprehensive review. Green Technologies and Sustainability, 3(3), 100199. https://doi.org/10.1016/j.grets.2025.100199

Wu, K., Ji, Z., Wang, H., Shao, X., Li, H., Zhang, W., Kong, W., Xia, J., & Bao, X. (2025). A Comprehensive Review of AI Methods in Agri-Food Engineering: Applications, Challenges, and Future Directions. Electronics, 14(20), 3994. https://doi.org/10.3390/electronics14203994

Zahlul Ikhsan, Muhammad Al-Ikhlas, Yaherwandi, Hasmiandy Hamid, Aulia Oktavia, & Dandy Ahamefula Osibe. (2024). Level of Pest Infestation on Cocoa (Theobroma cacao L.) Variety BL-50 in Tanah Datar Regency, West Sumatera Province, Indonesia. Andalasian International Journal of Entomology, 2(1), 38–47. https://doi.org/10.25077/aijent.2.1.38-47.2024

Publicado

2026-01-20

Cómo citar

Navarro-Cabrera, J. R., Beraún-Barrantes, J. G., Cárdenas-García, Ángel, & Lozano-Carranza, C. M. (2026). Aplicación de aprendizaje profundo en la detección fitosanitaria del cacao usando visión por computadora. Revista Científica De Sistemas E Informática, 6(1), e1385. https://doi.org/10.51252/rcsi.v6i1.1385