Using a Dataset to Create an Application for Detection of Problems in Strawberry Cultivation through Image Analysis

• Pedro Arthur Pinto da Silva Ortiz UFSM
• Daniel Lichtnow UFSM

DOI: https://doi.org/10.5753/erbd.2024.238696

Abstract

This work describes an image classification model generated for use in an application prototype designed to detect issues in strawberry. To generate the model, a dataset containing images of seven different types of diseases in strawberry cultivation was used, obtained from the Kaggle platform. The model implementation was carried out in the Ultralytics HUB analysis application, which provides real-time object detection and image recognition, optimizing the Machine Learning model training using GPUs. The work also employs the YOLOv8 architecture. The proposal aims to study and analyze ways to detect problems in plants, reducing the need for human analysis.

References

Abadi, M. et al. (2015) TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Software available from tensorflow.org. Disponível em: [link]

Afzaal, U. et al. (2021) An instance segmentation model for strawberry diseases based on mask r-cnn. Sensors, MDPI, v. 21, n. 19.

Jocher, G. et al (2023) YOLO by Ultralytics. Disponível em: [link]

Mahmud, M. S., et al (2020) Real-time detection of strawberry powdery mildew disease using a mobile machine vision system. Agronomy, 10(7), 1027.

Tripathi, M. K., & Maktedar, D. D. (2020). A role of computer vision in fruits and vegetables among various horticulture products of agriculture fields: A survey. Information Processing in Agriculture, 7(2), 183-203.

Wang, J., Yu, L., Yang, J., & Dong, H. (2021). Dba_ssd: A novel end-to-end object detection algorithm applied to plant disease detection. Information, 12(11), 474.

Zhao, S., Liu, J., & Wu, S. (2022). Multiple disease detection method for greenhouse-cultivated strawberry based on multiscale feature fusion Faster R_CNN. Computers and Electronics in Agriculture, 199, 107176.