Comparison of CNN Architectures via Transfer Learning for Avocado Fruit Disease Classification
DOI:
https://doi.org/10.67294/qjr9z363Keywords:
Avocado Diseases, Convolutional Neural Networks, VGG16, Precision Agriculture, Grad-CAMAbstract
Anthracnose and scab reduce the commercial quality of avocado fruit, and their visual diagnosis can be difficult when lesions present similar features. This study compares VGG16, ResNet50, EfficientNetB2, and InceptionV3 using transfer learning to classify healthy, anthracnose-infected, and scab-infected fruits. The protocol employed laboratory images: 569 for five-fold stratified cross-validation and 100 independent images for the final test. All four architectures were trained under the same two-phase tuning scheme, online data augmentation, class weighting, and evaluation using macro metrics; the selected model was further examined using a confusion matrix, ROC/AUC curves, and Grad-CAM. VGG16 achieved the best performance in cross-validation (accuracy = 0.817 ± 0.054; macro F1 = 0.808 ± 0.060), whereas InceptionV3 ranked fourth (macro F1 = 0.731 ± 0.038). In the independent test, VGG16 reached 74% accuracy and 0.72 macro F1. The main source of error was the classification of anthracnose as scab; likewise, anthracnose presented the lowest AUC (0.767). Grad-CAM maps concentrated attention on fruit lesions, although they constitute qualitative interpretive evidence. The results are limited to controlled conditions: no field images from Apurímac were used. Therefore, regional validation and deployment on lightweight devices are proposed as future work.
References
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8, 53. https://doi.org/10.1186/s40537-021-00444-8 DOI: https://doi.org/10.1186/s40537-021-00444-8
Ángel-García, C., Rodríguez-Arevalo, K. A., Murcia Riaño, N., Martínez-Caballero, L. N., Ceballos-Aguirre, G., Jaramillo Laverde, A., & Martínez, M. F. (2023). Molecular identification and fungal diversity associated with diseases in Hass avocado fruit grown in Cauca, Colombia. Pathogens, 12(12), 1418. https://doi.org/10.3390/pathogens12121418 DOI: https://doi.org/10.3390/pathogens12121418
Barragán López, R. C., Velazco Jiménez, J. E., & Martínez Pinto, C. A. (2024). Etiquetado de imágenes: Un enfoque efectivo para entrenar un modelo de visión artificial para la detección de plagas y enfermedades de aguacate con datos limitados. En Memorias del Congreso Internacional de Mecatrónica, Control e Inteligencia Artificial (CIMCIA 2024) (pp. 160–168). Universidad Nacional Autónoma de México, Facultad de Estudios Superiores Cuautitlán. https://virtual.cuautitlan.unam.mx/intar/memoriascimcia/wp-content/uploads/sites/20/2024/12/24-160-168-20.pdf
Belizaire, C. M., Gañán-Betancur, L., & Gazis, R. (2024). Avocado scab caused by Elsinoe perseae: A diagnostic guide. Plant Health Progress, 25(2), 218–225. https://doi.org/10.1094/PHP-10-23-0084-DG DOI: https://doi.org/10.1094/PHP-10-23-0084-DG
Campos-Ferreira, U. E., & González-Camacho, J. M. (2021). Clasificador de red neuronal convolucional para identificar enfermedades del fruto de aguacate (Persea americana Mill.) a partir de imágenes digitales. Agrociencia, 55(8), 695–709. https://doi.org/10.47163/agrociencia.v55i8.2662 DOI: https://doi.org/10.47163/agrociencia.v55i8.2662
Campos-Ferreira, U. E., González-Camacho, J. M., & Carrillo-Salazar, A. (2023). Automatic identification of avocado fruit diseases based on machine learning and chromatic descriptors. Revista Chapingo. Serie Horticultura, 29(3), 115–130. https://doi.org/10.5154/r.rchsh.2023.04.002 DOI: https://doi.org/10.5154/r.rchsh.2023.04.002
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. En 2009 IEEE Conference on Computer Vision and Pattern Recognition (pp. 248–255). IEEE. https://doi.org/10.1109/CVPR.2009.5206848 DOI: https://doi.org/10.1109/CVPR.2009.5206848
Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311–318. https://doi.org/10.1016/j.compag.2018.01.009 DOI: https://doi.org/10.1016/j.compag.2018.01.009
Flores, A., Guzmán-Valdivia, J., Huaquipaco, S., Tito-Chura, H., Morales-Gonzales, R., Silva-Delgado, C., & Flores-Quispe, E. (2026). A weighted ensemble of convolutional neural networks for anthracnose detection in avocado fruit. Computers, 15(6), 378. https://doi.org/10.3390/computers15060378 DOI: https://doi.org/10.3390/computers15060378
Food and Agriculture Organization. (2019). The State of Food and Agriculture 2019: Moving forward on food loss and waste reduction. Food and Agriculture Organization of the United Nations. https://doi.org/10.4060/CA6030EN DOI: https://doi.org/10.4060/CA6030EN
Haikal, A. L. A., Yudistira, N., & Ridok, A. (2024). Comprehensive mixed-based data augmentation for detection of rice leaf disease in the wild. Crop Protection, 184, 106816. https://doi.org/10.1016/j.cropro.2024.106816 DOI: https://doi.org/10.1016/j.cropro.2024.106816
Herrera-González, J. A., Bautista-Baños, S., Serrano, M., Ramos-Bell, S., & Gutiérrez-Martínez, P. (2024). Colletotrichum siamense causante de antracnosis en poscosecha de aguacate ‘Hass’. Revista Mexicana de Ciencias Agrícolas, 15(5), e3434. https://doi.org/10.29312/remexca.v15i5.3434 DOI: https://doi.org/10.29312/remexca.v15i5.3434
Hughes, D. P., & Salathé, M. (2015). An open access repository of images on plant health to enable the development of mobile disease diagnostics through machine learning and crowdsourcing. arXiv. https://arxiv.org/abs/1511.08060
Instituto Peruano de Economía. (2024, 15 de febrero). Apurímac: Producción agropecuaria se contrajo 6 % en el 2023. https://www.ipe.org.pe/portal/apurimac-produccion-agropecuaria-se-contrajo-6-en-el-2023/
Khan, A. T., Jensen, S. M., Khan, A. R., & Li, S. (2023). Plant disease detection model for edge computing devices. Frontiers in Plant Science, 14, 1308528. https://doi.org/10.3389/fpls.2023.1308528 DOI: https://doi.org/10.3389/fpls.2023.1308528
Li, M., Zhou, G., Chen, A., Yi, J., Lu, C., He, M., & Hu, Y. (2022). FWDGAN-based data augmentation for tomato leaf disease identification. Computers and Electronics in Agriculture, 194, 106779. https://doi.org/10.1016/j.compag.2022.106779 DOI: https://doi.org/10.1016/j.compag.2022.106779
Llanos, A. K., Bustamante, M. I., Elfar, K., Vicuña, A., Morales, D., Escobedo, V., Carrillo, J. D., Apaza-Tapia, W., & Eskalen, A. (2026). Identification, distribution, and pathogenicity of Lasiodiplodia species causing avocado stem-end rot in Peru. Plant Disease, 110(6), 2332–2341. https://doi.org/10.1094/PDIS-08-25-1691-RE DOI: https://doi.org/10.1094/PDIS-08-25-1691-RE
Majeed, Y., Ojo, M. O., & Zahid, A. (2024). Standalone edge AI-based solution for tomato diseases detection. Smart Agricultural Technology, 9, 100547. https://doi.org/10.1016/j.atech.2024.100547 DOI: https://doi.org/10.1016/j.atech.2024.100547
Matsui, T., Kamata, T., Koseki, S., & Koyama, K. (2022). Development of automatic detection model for stem-end rots of ‘Hass’ avocado fruit using X-ray imaging and image processing. Postharvest Biology and Technology, 192, 111996. https://doi.org/10.1016/j.postharvbio.2022.111996 DOI: https://doi.org/10.1016/j.postharvbio.2022.111996
Matsui, T., Sugimori, H., Koseki, S., & Koyama, K. (2023). Automated detection of internal fruit rot in Hass avocado via deep learning-based semantic segmentation of X-ray images. Postharvest Biology and Technology, 203, 112390. https://doi.org/10.1016/j.postharvbio.2023.112390 DOI: https://doi.org/10.1016/j.postharvbio.2023.112390
Mishra, S., Ayane, T. H., Ellappan, V., Rathee, D. S., & Kalla, H. (2022). Avocado fruit disease detection and classification using modified SCA–PSO algorithm-based MobileNetV2 convolutional neural network. Iran Journal of Computer Science, 5(4), 345–358. https://doi.org/10.1007/s42044-022-00116-7 DOI: https://doi.org/10.1007/s42044-022-00116-7
Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419. https://doi.org/10.3389/fpls.2016.01419 DOI: https://doi.org/10.3389/fpls.2016.01419
Moreano, M., Sosa, A., Mauricio, D., Rivera, L., & Santisteban, J. (2026). ApaltAI: A web-based diagnostic system with a sequential voting architecture for detecting anthracnose and scab in avocado fruit. Frontiers in Plant Science, 17, 1736123. https://doi.org/10.3389/fpls.2026.1736123 DOI: https://doi.org/10.3389/fpls.2026.1736123
Morellos, A., Pantazi, X. E., Paraskevas, C., & Moshou, D. (2022). Comparison of deep neural networks in detecting field grapevine diseases using transfer learning. Remote Sensing, 14(18), 4648. https://doi.org/10.3390/rs14184648 DOI: https://doi.org/10.3390/rs14184648
Mostafa, S., Mondal, D., Panjvani, K., Kochian, L., & Stavness, I. (2023). Explainable deep learning in plant phenotyping. Frontiers in Artificial Intelligence, 6, 1203546. https://doi.org/10.3389/frai.2023.1203546 DOI: https://doi.org/10.3389/frai.2023.1203546
Muhammad, A., Salman, Z., Lee, K., & Han, D. (2023). Harnessing the power of diffusion models for plant disease image augmentation. Frontiers in Plant Science, 14, 1280496. https://doi.org/10.3389/fpls.2023.1280496 DOI: https://doi.org/10.3389/fpls.2023.1280496
Nagaraju, M., & Chawla, P. (2020). Systematic review of deep learning techniques in plant disease detection. International Journal of System Assurance Engineering and Management, 11(3), 547–560. https://doi.org/10.1007/s13198-020-00972-1 DOI: https://doi.org/10.1007/s13198-020-00972-1
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. En Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626). https://doi.org/10.1109/ICCV.2017.74 DOI: https://doi.org/10.1109/ICCV.2017.74
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. En Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2818–2826). IEEE. https://doi.org/10.1109/CVPR.2016.308 DOI: https://doi.org/10.1109/CVPR.2016.308
Thakur, P. S., Chaturvedi, S., Khanna, P., Sheorey, T., & Ojha, A. (2023). Vision transformer meets convolutional neural network for plant disease classification. Ecological Informatics, 77, 102245. https://doi.org/10.1016/j.ecoinf.2023.102245 DOI: https://doi.org/10.1016/j.ecoinf.2023.102245
Thangaraj, R., Anandamurugan, S., & Kaliappan, V. K. (2021). Automated tomato leaf disease classification using transfer learning-based deep convolution neural network. Journal of Plant Diseases and Protection, 128(1), 73–86. https://doi.org/10.1007/s41348-020-00403-0 DOI: https://doi.org/10.1007/s41348-020-00403-0
Upadhyay, A., Chandel, N. S., Singh, K. P., Chakraborty, S. K., Nandede, B. M., Kumar, M., Subeesh, A., Upendar, K., Salem, A., & Elbeltagi, A. (2025). Deep learning and computer vision in plant disease detection: A comprehensive review of techniques, models, and trends in precision agriculture. Artificial Intelligence Review, 58, 92. https://doi.org/10.1007/s10462-024-11100-x DOI: https://doi.org/10.1007/s10462-024-11100-x
United Nations. (2015). Transformar nuestro mundo: La Agenda 2030 para el Desarrollo Sostenible (A/RES/70/1). https://undocs.org/es/A/RES/70/1
Valle-Medina, F. D., Castillo-Heredia, L. J., Correa-Peralta, M. A., & Guzmán Seraquive, J. E. (2025). Clasificación de enfermedades en hojas de papa utilizando transformadores de visión. Novasinergia, 8(1), 142–156. https://doi.org/10.37135/ns.01.15.06 DOI: https://doi.org/10.37135/ns.01.15.06
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 DOI: https://doi.org/10.3390/agriculture12091487
Zhou, Z., Zhang, Y., Gu, Z., & Yang, S. X. (2023). Deep learning approaches for object recognition in plant diseases: A review. Intelligent Robotics, 3(4), 514–537. https://doi.org/10.20517/ir.2023.29 DOI: https://doi.org/10.20517/ir.2023.29
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Marco Antonio Mejia Llamocca (Author); Dr. Manuel J. Ibarra-Cabrera (Translator)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
