Development of an artificial intelligence model integrated into a mobile application for detecting diseases in avocado fruits
Article Sidebar
Main Article Content
Abstract
This study aimed to develop an artificial intelligence model integrated into a mobile application for the detection of diseases in Fuerte avocado (Persea americana Mill.) fruits. Computer vision techniques based on the YOLOv8l (Large) architecture were employed. The dataset, obtained from the Kaggle platform, originally consisted of 1,980 images and was expanded through data augmentation techniques to 5,014 images in order to improve the model's generalization capability. The system successfully identified the classes anthracnose, scab, and healthy fruits, achieving a mAP50 of 0.956 and an F1-score of 0.929, demonstrating satisfactory performance during model evaluation. Subsequently, the model was converted to the TensorFlow Lite (float32) format and integrated into a mobile application developed in Android Studio (Java), enabling on-device inference without an internet connection. Functional tests performed on an Android mobile device showed average processing times of 3 to 4 seconds per image, with stable performance in both camera and gallery analysis modes. Overall, the proposed system constitutes a supporting tool for phytosanitary monitoring, contributing to the early detection of diseases in avocado cultivation.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
When an author creates an article and publishes it in a journal, the copyright passes to the journal as part of the publishing agreement. Therefore, the journal becomes the owner of the rights to reproduce, distribute and sell the article. The author retains some rights, such as the right to be recognized as the creator of the article and the right to use the article for his or her own scholarly or research purposes, unless otherwise agreed in the publication agreement.
How to Cite
References
U. E. Campos-Ferreira, J. M. González-Camacho, and A. Carrillo-Salazar, "Automatic identifica-tion of avocado fruit diseases based on machine learn-ing and chromatic descriptors," Rev. Cha-pingo Ser. Hortic., vol. 29, no. 3, pp. 115-130, Sep. 2023.
https://doi.org/10.5154/r.rchsh.2023.04.002
A. Tapia Rodríguez, J. F. Ramírez Dávila, M. L. Salgado Siclán, Á. Castañeda Vildózola, F. I. Mal-donado Zamora, and A. V. Lara Díaz, "Spatial dis-tribution of anthracnose (Colletotrichum gloeo-sporioides Penz) in avocado in the State of Mexico, Mexico," Rev. Argent. Microbiol., vol. 52, no. 1, pp. 72-81, Jan. 2020.
https://doi.org/10.1016/j.ram.2019.07.004
J. A. Herrera-González, S. Bautista-Baños, M. Ser-rano, S. Ramos-Bell, and P. Gutiérrez-Martínez, "Colletotrichum siamense causante de antracno-sis en poscosecha de aguacate 'Hass'," Rev. Mex. Cienc. Agric., vol. 15, no. 5, Jul. 2024.
https://doi.org/10.29312/remexca.v15i5.3434
INTAGRI, “Antracnosis en el cultivo de agua-cate,” Artículos Técnicos de Intagri, vol. 4, no. 81, 2017. [Online]. Available: https://www.intagri.com/articulos/fitosanidad/antracnosis-en-el-cultivo-de-aguacate
E. Trinidad Angel, F. de J. Ascencio Valle, J. Ar-mando Ulloa, J. C. Ramirez Ramirez, and J. A. Ragazzo Sanchez, "Identificación y caracter-ización de Colletotrichum spp. causante de an-tracnosis en aguacate" Nayarit, México," vol. 1, no. 19, pp. 3953-3964, Nov. 2017.
https://doi.org/10.29312/remexca.v0i19.664
S. Mishra, T. H. Ayane, V. Ellappan, D. S. Rathee, and H. Kalla, "Avocado fruit disease detection and classification using modified SCA-PSO algo-rithm-based MobileNetV2 convolutional neural net-work," Iran J. Comput. Sci., vol. 5, no. 4, pp. 345-358, Dec. 2022.
https://doi.org/10.1007/s42044-022-00116-7
K. P. Ferentinos, "Deep learning models for plant disease detection and diagnosis," Comput. Elec-tron. Agric., vol. 145, pp. 311-318, Feb. 2018.
https://doi.org/10.1016/j.compag.2018.01.009
E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, "A comparative study of fine-tuning deep learning models for plant disease identification," Comput. Electron. Agric., vol. 161, pp. 272-279, Jun. 2019.
https://doi.org/10.1016/j.compag.2018.03.032
A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, Apr. 2020. [Online]. Available: http://arxiv.org/abs/2004.10934
J. Redmon, S. Divvala, R. Girshick, and A. Far-hadi, "You Only Look Once: Unified, real-time ob-ject de-tection," arXiv preprint arXiv:1506.02640, May 2016. [Online]. Available: http://arxiv.org/abs/1506.02640
https://doi.org/10.1109/CVPR.2016.91
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," arXiv pre-print arXiv:2207.02696, Jul. 2022. [Online]. Availa-ble: http://arxiv.org/abs/2207.02696
https://doi.org/10.1109/CVPR52729.2023.00721
Y. Wang et al., "Enhanced multiscale plant dis-ease detection with the PYOLO model innova-tions," Sci. Rep., vol. 15, 2025, art. 5179.
https://doi.org/10.1038/s41598-025-89034-9
L. Guadalima-Inga, R. Lojano-Chavez, and M. Cabrera-Sarango, “Inteligencia artificial en sani-dad vegetal,” 2020. Accessed: May 20, 2026. [Online]. Available: https://virtual.cuautitlan.unam.mx/intar/ceiaait/wp-content/uploads/sites/14/2021/03/7-Art%C3%ADculos-editados-55-61.pdf
D. Pineda Medina et al., “Sistema para el di-agnóstico de plagas de Solanum tuberosum L. mediante técnicas de inteligencia artificial,” Rev. Prot. Veg., vol. 38, no. 3, pp. 1–6, 2023. [Online]. Available: https://cu-id.com/2247/v38e16
B. Roldan Ortega, R. Roshan Biswal, and E. Sanchez de la Cruz, "Detección de enfermedades en el sector agrícola utilizando inteligencia artifi-cial," Res. Comput. Sci., vol. 148, no. 7, pp. 419-427, 2019. [Online]. Available: https://rcs.cic.ipn.mx/2019_148_7/Deteccion%20de%20enfermedades%20en%20el%20sector%20agrico-la%20utilizando%20Inteligencia%20Artificial.pdf
https://doi.org/10.13053/rcs-148-7-31
G. T. Castro Alvarez, “Aplicación de algoritmos inteligentes para reconocimiento automático de enfermedades foliares de cultivo de palta,” tesis de grado, Ilo, Perú, 2019. [Online]. Available: https://repositorio.unam.edu.pe/items/e3e92514-188c-4972-9921-afabe6236a03
E. D. Cabrera Herrera, “Aplicación web usando deep learning aplicado al reconocimiento de plagas y enfermedades para mejorar el trata-miento de los cultivos de papa Yungay en Cuter-vo-Angurra,” tesis de grado, Chiclayo, Perú, 2025. [Online]. Available: https://orcid.org/0000-0003-1178-0519
B. R. J. Huaman Caceres, “Machine learning para la detección de plagas en las hojas del tomate Abancay 2022,” tesis de grado, Univ. Nac. Micae-la Bastidas de Apurímac, Abancay, Perú, 2025. [Online]. Available: https://repositorio.unamba.edu.pe/items/379b774c-4385-4756-a6e1-2ab7fdc74adf
J. M. Medina Cercado and J. A. Urteaga Montoya, “Impacto de la aplicación móvil ‘Healthy Plant’ para detectar enfermedades foliares en cultivos de aguaymanto haciendo uso de inteligencia arti-ficial con Custom Vision en la ciudad de Ca-jamarca 2021,” tesis de grado, Univ. Privada del Norte, Cajamarca, Perú, 2021. [Online]. Availa-ble: https://repositorio.upn.edu.pe/item/d8ea424d-3c96-4d84-acc8-475c1d12ddb3
N. A. Alvarez Vargas, “Detección de enferme-dades en el cultivo de papa mediante el uso de machine learning en Abancay, 2022,” tesis de grado, Univ. Nac. Micaela Bastidas de Apurímac, Abancay, Perú, 2025. [Online]. Available: https://repositorio.unamba.edu.pe/items/3b6581d1-8b23-427a-a25d-316aafe09554
P. Jeet et al., “Disease detection in fruits and veg-etables using machine learning with OpenVINO technology,” vol. 1, no. 1, 2025.
https://doi.org/10.62762/DA.2025.743124
J. Navarro Cruz, “Diseño de un sistema automát-ico de reconocimiento de patrones para la clasifi-cación de palta en la comunidad de Mollebamba-Chincheros,” tesis de grado, Univ. Nac. José Ma-ría Arguedas, Andahuaylas, Perú, 2023. [Online]. Available:https://reposit rio.unajma.edu.pe/item/b7426bc2-48a5-4559-bf50-5c580dc9f4c7
A. Koirala, K. B. Walsh, Z. Wang, and C. McCar-thy, "Deep learning - Method overview and re-view of use for fruit detection and yield estima-tion," Com-put. Electron. Agric., vol. 162, pp. 219-234, Jul. 2019.
https://doi.org/10.1016/j.compag.2019.04.017
A. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, "A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition," Sen-sors, vol. 17, no. 9, Sep. 2017.
https://doi.org/10.3390/s17092022
C. Shorten and T. M. Khoshgoftaar, "A survey on image data augmentation for deep learning," J. Big Data, vol. 6, no. 1, Dec. 2019.
https://doi.org/10.1186/s40537-019-0197-0
L. Liu et al., "Deep learning for generic object detec-tion: A survey," Int. J. Comput. Vis., vol. 128, no. 2, pp. 261-318, Feb. 2020.
https://doi.org/10.1007/s11263-019-01247-4
A. Picon, A. Alvarez-Gila, M. Seitz, A. Ortiz-Barredo, J. Echazarra, and A. Johannes, "Deep con-volutional neural networks for mobile cap-ture de-vice-based crop disease classification in the wild," Comput. Electron. Agric., vol. 161, pp. 280-290, Jun. 2019.
https://doi.org/10.1016/j.compag.2018.04.002
F. P. Lara Galicia, “Guía sobre Google Colab: Aprendizaje y soluciones en programación Py-thon.” 2024. [Online]. Available: https://www.godaddy.com/resources/latam/desarrollo/google-colab-que-es-como-utilizarlo
V. Nguyen, A. Tao, O. Gallo, J. Lisiecki, and A. Badki, “Improving computer vision with NVID-IA A100 GPUs.” 2020. [Online]. Available: https://developer.nvidia.com/blog/improving-computer-vision-with-nvidia-a100-gpus/
J. Lee et al., “On-device neural net inference with mobile GPUs,” arXiv preprint arXiv:1907.01989, Jul. 2019. [Online]. Available: http://arxiv.org/abs/1907.01989
R. Lopez Lucia, “Aplicación Android y servicio web Spring para la detección y registro de señales de tráfico de velocidad usando deep learning con tiny-YOLOv3 y OpenCV,” tesis de grado, 2020. [Online]. Available: https://idus.us.es/items/dcbf6484-cef0-4b70-a438-a365c74b0c4a
R. A. Solis Villanueva, “Modelo inteligente basado en técnicas de inteligencia artificial y su impacto en el desarrollo de aplicaciones en los dispositivos móviles,” Lima, Perú, 2019. [Online]. Available: https://repositorio.unfv.edu.pe/items/929c2d8c-a7ca-4e25-8414-d05afbcf45fe