Clasificación de imágenes de manchas marrones en cacao mediante visión artificial y transferencia de conocimiento en la región de San Martín
DOI:
https://doi.org/10.55873/sns7vf68Palabras clave:
aprendizaje profundo, clasificación binaria, fitopatología digital, redes neuronales convolucionales, visión por computadoraResumen
La mancha parda afecta la productividad y calidad del cacao, generando pérdidas económicas en la región San Martín. El estudio tuvo como objetivo diseñar un sistema para clasificar imágenes de frutos de cacao afectados por esta enfermedad mediante visión artificial y transferencia de aprendizaje en condiciones reales de campo. La investigación se desarrolló en Chazuta durante 2024. Se recopilaron 3.003 imágenes de frutos sanos y enfermos, segmentadas mediante Mask R-CNN y sometidas a aumento de datos, obteniéndose 12.012 imágenes. Se evaluaron las arquitecturas preentrenadas VGG16, ResNet50 y MobileNetV2 como extractores de características, combinadas con máquinas de vectores de soporte (SVM). El desempeño se evaluó mediante validación cruzada y análisis estadísticos con las pruebas de Levene, ANOVA y Tukey. Todos los modelos superaron el 98,6 % de precisión; VGG16 + SVM alcanzó el mejor desempeño, con una precisión promedio del 99,51 % y diferencias estadísticamente significativas frente a los demás modelos. Se concluye que el enfoque híbrido basado en extracción profunda de características y clasificación mediante SVM es eficaz para detectar automáticamente la mancha parda del cacao y presenta potencial de aplicación en agricultura de precisión.
Descargas
Referencias
Al Sahili, Z., & Awad, M. (2022). The power of transfer learning in agricultural applications: AgriNet. arXiv. https://arxiv.org/abs/2207.03881v3
Albaaji, G. F., & S.S., V. C. (2023). Artificial intelligence SoS framework for sustainable agricultural production. Computers and Electronics in Agriculture, 213, 108182. https://doi.org/10.1016/j.compag.2023.108182
Alomar, K., Aysel, H. I., & Cai, X. (2023). Data augmentation in classification and segmentation: A survey and new strategies. Journal of Imaging, 9(2), 46. https://doi.org/10.3390/jimaging9020046
Aly, M., & Behiry, M. H. (2025). Enhancing anomaly detection in IoT-driven factories using Logistic Boosting, Random Forest, and SVM: A comparative machine learning approach. Scientific Reports, 15(1), 23694. https://doi.org/10.1038/s41598-025-08436-x
Anduyan, D., Cabillo, N., Gultiano, N., & Pacot, M. P. (2025). Enhancing cocoa pod disease classification via transfer learning and ensemble methods: Toward robust predictive modeling. arXiv. https://arxiv.org/abs/2504.12992
Arham, Z., et al. (2024). Green pesticide high activity based on TiO2 nanosuspension incorporated silver microspheres against Phytophthora palmivora. Indian Journal of Microbiology. https://doi.org/10.1007/s12088-024-01239-0
Ariawan, K. R., Ekayana, A. A. G., Indrawan, I. P. Y., Winatha, K. R., & Setiawan, I. N. A. F. (2025). Performance comparasion of DenseNet-121 and MobileNetV2 for cacao fruit disease image classification. Indonesian Journal of Data and Science, 6(1), 30–38. https://doi.org/10.56705/ijodas.v6i1.233
Araujo Horna, L. J. (2023). Propagación en cacao (Theobroma cacao L.) en la región San Martín durante los últimos cinco años. Universidad Nacional de San Martín.
Ayikpa, K. J., Mamadou, D., Gouton, P., & Adou, K. J. (2023). Classification of cocoa pod maturity using similarity tools on an image database: Comparison of feature extractors and color spaces. Data, 8(6), 99. https://doi.org/10.3390/data8060099
Becerra, L. D., Quintanilla-Carvajal, M. X., Escobar, S., & Ruiz, R. Y. (2023). Correlation between color parameters and bioactive compound content during cocoa seed transformation under controlled process conditions. Food Bioscience, 53, 102526. https://doi.org/10.1016/j.fbio.2023.102526
Becerra, L. D., Quintanilla-Carvajal, M. X., Escobar, S., & Ruiz Pardo, R. Y. (2024). From controlled transformed cocoa beans to chocolate: Bioactive properties, metabolomic profile, and in vitro bioaccessibility. Food Chemistry, 433, 137321. https://doi.org/10.1016/j.foodchem.2023.137321
Borromeo, K. O., Bonotan, M. R., Llagas, A. P., Juan, J. M. O., Sanchez, P. D. C., & Berro, N. K. A. (2025). Classification of cacao pods ripeness using convolutional neural networks. Procedia Computer Science, 257, 1197–1204. https://doi.org/10.1016/j.procs.2025.03.160
Buenaño Vera, D., Oviedo, B., Chiriboga Casanova, W., & Zambrano-Vega, C. (2024). Deep learning-based computational model for disease identification in cocoa pods (Theobroma cacao L.). arXiv. https://doi.org/10.48550/arXiv.2401.01247
Cano Ortega, C., & Pineda Molina, J. (2023). Development of a mobile application for the detection of diseases in cocoa fruits. http://hdl.handle.net/10554/65284
Christakakis, P., et al. (2024). Smartphone-based citizen science tool for plant disease and insect pest detection using artificial intelligence. Technologies, 12(7), 101. https://doi.org/10.3390/technologies12070101
Cortez, D., et al. (2024). From the seed to the cocoa liquor: Traceability of bioactive compounds during the postharvest process of cocoa in Amazonas-Peru. Microchemical Journal, 201, 110607. https://doi.org/10.1016/j.microc.2024.110607
De la Peña, N., & Granados, O. M. (2023). Artificial intelligence solutions to reduce information asymmetry for Colombian cocoa small-scale farmers. Information Processing in Agriculture. https://doi.org/10.1016/j.inpa.2023.03.001
Delgado, C., Couturier, G., Balcazar, L., & Chichipe, A. (2023). Insect pests of Theobroma cacao (Malvaceae) in the Peruvian Amazon. Tropical Agriculture, 100(2), 110–114.
Eric, O., Gyening, R.-M. O. M., Appiah, O., Takyi, K., & Appiahene, P. (2023). Cocoa beans classification using enhanced image feature extraction techniques and a regularized artificial neural network model. Engineering Applications of Artificial Intelligence, 125, 106736. https://doi.org/10.1016/j.engappai.2023.106736
Figiel, S. (2022). Development of artificial intelligence and potential impact of its applications in agriculture on labor use and productivity. Zagadnienia Ekonomiki Rolnej / Problems of Agricultural Economics, 373(4), 5–21. https://doi.org/10.30858/zer/153583
Gopalakrishna, K. M., & Lingaraju, R. M. (2025). A prediction of coconut and coconut leaf disease using MobileNetV2 based classification. International Journal of Electrical and Computer Engineering, 15(3), 2834–2844. https://doi.org/10.11591/ijece.v15i3.pp2834-2844
Huang, X., Peng, D., Qi, H., Zhou, L., & Zhang, C. (2024). Detection and instance segmentation of grape clusters in orchard environments using an improved Mask R-CNN model. Agriculture, 14(6), 918. https://doi.org/10.3390/agriculture14060918
J., 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
Javaid, M., Haleem, A., Khan, I. H., & Suman, R. (2023). Understanding the potential applications of artificial intelligence in agriculture sector. Advanced Agrochem, 2(1), 15–30. https://doi.org/10.1016/j.aac.2022.10.001
Jesse, A., Douha, N. Y.-R., & Lenka, P. (2024). Image classification for CSSVD detection in cacao plants. arXiv. https://arxiv.org/abs/2405.04535
Karim, M. J., Goni, M. O. F., Nahiduzzaman, M., Ahsan, M., Haider, J., & Kowalski, M. (2024). Enhancing agriculture through real-time grape leaf disease classification via an edge device with a lightweight CNN architecture and Grad-CAM. Scientific Reports, 14(1), 16022. https://doi.org/10.1038/s41598-024-66989-9
Khan, M., et al. (2024). Ensemble and optimization algorithm in support vector machines for classification of wheat genotypes. Scientific Reports, 14(1), 22728. https://doi.org/10.1038/s41598-024-72056-0
Kouassi, K. S., Diarra, M., Edi, K. H., & Koua, B. J.-C. (2024). Detection of cocoa leaf diseases using the CNN-based feature extractor and XGBOOST classifier. Open Journal of Applied Sciences, 14(10), 2955–2972. https://doi.org/10.4236/ojapps.2024.1410193
Kouassi, K. S., Diarra, M., Edi, K. H., & Koua, B. J.-C. (2025). Detection of cocoa pod diseases using a hybrid feature extractor combining CNN and vision transformer with dual classifier. Edelweiss Applied Science and Technology, 9(1), 668–681. https://doi.org/10.55214/25768484.v9i1.4209
Lomotey, R. K., Kumi, S., Orji, R., & Deters, R. (2024). Automatic detection and diagnosis of cocoa diseases using mobile tech and deep learning. International Journal of Sustainable Agricultural Management and Informatics, 10(1), 92–119. https://doi.org/10.1504/IJSAMI.2024.135403
Lopes, J. F., da Costa, V. G. T., Barbin, D. F., Cruz-Tirado, L. J. P., Baeten, V., & Barbon Junior, S. (2022). Deep computer vision system for cocoa classification. Multimedia Tools and Applications, 81(28), 41059–41077. https://doi.org/10.1007/s11042-022-13097-3
Lumumba, V., Kiprotich, D., Mpaine, M., Makena, N., & Kavita, M. (2024). Comparative analysis of cross-validation techniques: LOOCV, K-folds cross-validation, and repeated K-folds cross-validation in machine learning models. American Journal of Theoretical and Applied Statistics, 13(5), 127–137. https://doi.org/10.11648/j.ajtas.20241305.13
Malakouti, S. M., Menhaj, M. B., & Suratgar, A. A. (2023). The usage of 10-fold cross-validation and grid search to enhance ML methods performance in solar farm power generation prediction. Cleaner Engineering and Technology, 15, 100664. https://doi.org/10.1016/j.clet.2023.100664
Marković, D., Stamenković, Z., Đorđević, B., & Ranđić, S. (2024). Image processing for smart agriculture applications using cloud-fog computing. Sensors, 24(18), 5965. https://doi.org/10.3390/s24185965
Martinović, M., Dokic, K., & Pudić, D. (2025). Comparative analysis of machine learning models for predicting innovation outcomes: An applied AI approach. Applied Sciences, 15(7), 3636. https://doi.org/10.3390/app15073636
Mduma, N., & Laizer, H. (2023). Machine learning imagery dataset for maize crop: A case of Tanzania. Data in Brief, 48, 109108. https://doi.org/10.1016/j.dib.2023.109108
Ministerio de Desarrollo Agrario y Riego. (2023). Observatorio de commodities: Cacao. https://cdn.www.gob.pe/uploads/document/file/5264502/%20Commodities%20Cacao%3A%20ene-mar%202023.pdf?v=1697059698
Muzuni, Ambardini, S., Widyaningsih, A. S., & Ismaun. (2023). Morphological and physiological characteristics of cocoa (Theobroma cacao L. var. criollo) infected by Phytophthora palmivora in cocoa plantations in Southeast Sulawesi Indonesia. AIP Conference Proceedings, 020015. https://doi.org/10.1063/5.0138524
Mwinami, N. V., Dulle, F. W., & Mtega, W. P. (2024). Data preservation practices for enhancing agricultural research data usage among agricultural researchers in Tanzania. Journal of Librarianship and Information Science, 56(1), 198–210. https://doi.org/10.1177/09610006221138110
Nyarko, B. N. E., Wu, W., Zhou, Z. J., & Mohd, M. J. (2024). Improved YOLOv5m model based on Swin Transformer, K-means++, and EIoU loss function for cocoa tree disease detection. Journal of Plant Protection Research, 64(3), 265–274. https://doi.org/10.24425/jppr.2024.151253
Oh, K. E. (2024). A comprehensive investigation of researchers’ shared file management practices in cloud storage. Human–Computer Interaction, 1–20. https://doi.org/10.1080/07370024.2024.2310551
Pei, G., Qian, X., Zhou, B., Liu, Z., & Wu, W. (2025). Research on agricultural disease recognition methods based on very large Kernel convolutional network-RepLKNet. Scientific Reports, 15(1), 16843. https://doi.org/10.1038/s41598-025-01553-7
Philips Paredes, M. H. (2022). Modelo de asociatividad para la mejora de la competitividad de las pymes productoras de cacao de la región San Martín. Universidad Nacional de San Martín.
Raut, R., et al. (2024). Transfer learning based leaf disease detection model using convolution neural network. Indonesian Journal of Electrical Engineering and Computer Science, 36(3), 1857–1865. https://doi.org/10.11591/ijeecs.v36.i3.pp1857-1865
Restrepo-Arias, J. F., Montoya-Castaño, M. J., Moreno-De La Espriella, M. F., & Branch-Bedoya, J. W. (2025). An application of deep learning models for the detection of cocoa pods at different ripening stages: An approach with Faster R-CNN and Mask R-CNN. Computation, 13(7), 159. https://doi.org/10.3390/computation13070159
Rios-Jara, J., & Lévano-Rodríguez, D. (2022). Importancia de los dispositivos usados en la fermentación de cacao (Theobroma cacao L.). Revista Agrotecnológica Amazónica, 2(1). https://doi.org/10.51252/raa.v2i1.281
Rodríguez Delzo, E. E., Huerta Guillén, R., & Montañez Artica, A. G. (2023). Identificación de variables que mejoren la cadena productiva de cacao (Theobroma cacao L.) y su importancia para el desarrollo del VRAEM – Perú. Revista Agrotecnológica Amazónica, 3(2).
Rojas Castillo, J. A. (2024). Identificación y distribución de Phytophthora spp., agente causante de la pudrición negra del fruto de cacao (Theobroma cacao L.) en la Amazonia Noroccidental. Universidad Nacional de Colombia. https://repositorio.unal.edu.co/handle/unal/86413
Rola, J. B., et al. (2024). Convolutional neural network model for cacao Phytophthora palmivora disease recognition. International Journal of Advanced Computer Science and Applications, 15(8). https://doi.org/10.14569/IJACSA.2024.0150897
Shafik, W., Tufail, A., De Silva Liyanage, C., & Apong, R. A. A. H. M. (2024). Using transfer learning-based plant disease classification and detection for sustainable agriculture. BMC Plant Biology, 24(1), 136. https://doi.org/10.1186/s12870-024-04825-y
Soh, K. S., Moung, E. G., Danker, K. J. J., Dargham, J. A., & Farzamnia, A. (2024). Cocoa diseases classification using deep learning algorithm. ITM Web of Conferences, 63, 01014. https://doi.org/10.1051/itmconf/20246301014
Sonmez, M. E., Sabanci, K., & Aydin, N. (2024). Convolutional neural network-support vector machine-based approach for identification of wheat hybrids. European Food Research and Technology, 250(5), 1353–1362. https://doi.org/10.1007/s00217-024-04473-4
Sousa-Ortega, C., Alcántara, C., Leon, R. G., Barranco-Elena, D., & Saavedra, M. (2024). The impact of burial depth on Centaurea diluta emergence and modelling of its growth using a nonlinear regression and artificial neural network. Pest Management Science, 80(3), 1182–1192. https://doi.org/10.1002/ps.7848
Sudjud, S., Jamil, M., & Melati, R. (2025). Development of cocoa pod rot disease identification model using You Only Look Once (YOLO-v9). Mathematical Modelling of Engineering Problems, 12(4). https://doi.org/10.18280/mmep.120418
Sunaryanto, R., Dewi, Y. S., Nurhayati, N., & Sitompul, J. (2024). Isolation and screening of actinomycetes active against plant pathogenic fungi. AIP Conference Proceedings, 040003. https://doi.org/10.1063/5.0194400
Tantiphanwadi, P., & Malithong, K. (2022). Bread browning stage classification model using VGG-16 transfer learning and fine-tuning with small training dataset. Engineering Journal, 26(11), 1–12. https://doi.org/10.4186/ej.2022.26.11.1
Taspinar, Y. S., Dogan, M., Cinar, I., Kursun, R., Ozkan, I. A., & Koklu, M. (2022). Computer vision classification of dry beans (Phaseolus vulgaris L.) based on deep transfer learning techniques. European Food Research and Technology, 248(11), 2707–2725. https://doi.org/10.1007/s00217-022-04080-1
Tello Púa, A. N., & Flores Ramírez, R. J. (2022). Lineamientos arquitectónicos de diseño de una planta industrial de cacao para mejorar la economía de la población de Chazuta, 2019.
Uzer, M. S. (2025). Deep learning-based classification consisting of pre-trained models and proposed model using K-fold cross-validation for pistachio species. Applied Sciences, 15(8), 4516. https://doi.org/10.3390/app15084516
Vargas Ramírez, M. (2023). Nivel de conocimiento sobre fertilización de suelos de los productores cacaoteros de la provincia Mariscal Cáceres. Universidad Nacional de San Martín.
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
Villamonte, A. F., Silva, P. J. S., Ronquillo, D. G. D., Rosales, M. A., Bandala, A. A., & Dadios, E. P. (2021). Python based defect classification of Theobroma cacao bean using fine-tuned Visual Geometry Group16. In 2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM) (pp. 1–6). IEEE. https://doi.org/10.1109/HNICEM54116.2021.9731887
Xu, M., Park, J.-E., Lee, J., Yang, J., & Yoon, S. (2024). Plant disease recognition datasets in the age of deep learning: Challenges and opportunities. Frontiers in Plant Science, 15. https://doi.org/10.3389/fpls.2024.1452551
Yang, C., Teng, Z., Dong, C., Lin, Y., Chen, R., & Wang, J. (2022). In-field citrus disease classification via convolutional neural network from smartphone images. Agriculture, 12(9), 1487. https://doi.org/10.3390/agriculture12091487
Zhou, Y., Zhu, Y., & Wong, W. K. (2023). Statistical tests for homogeneity of variance for clinical trials and recommendations. Contemporary Clinical Trials Communications, 33, 101119. https://doi.org/10.1016/j.conctc.2023.101119
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Aldahir Eduardo Altamirano-Reategui, Cristian Werner García-Estrella, Jhosep Sánchez-Flores
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
