Visualizing Plant Disease Distribution and Evaluating Model Performance for Deep Learning Classification with YOLOv8
2024

Using YOLOv8 to Detect Plant Diseases

Sample size: 1530 publication Evidence: high

Author Information

Author(s): Ghafar Abdul, Chen Caikou, Atif Ali Shah Syed, Ur Rehman Zia, Rahman Gul

Primary Institution: College of Information Engineering, Yangzhou University, Yangzhou, China

Hypothesis

Can YOLOv8 effectively detect and classify various plant diseases in real-time?

Conclusion

The YOLOv8 model demonstrated high accuracy in classifying plant conditions, including diseases, even with unseen data.

Supporting Evidence

  • The YOLOv8 model was rigorously tested on a dataset of 1530 images.
  • The model achieved high accuracy in classifying plant conditions.
  • Results showed the model's effectiveness in real-world scenarios with unseen data.
  • Data augmentation techniques were applied to enhance model robustness.
  • Custom anchor boxes improved detection of specific disease symptoms.

Takeaway

This study shows that a computer program can quickly tell if a plant is sick or healthy by looking at pictures of its leaves.

Methodology

The study used a custom-trained YOLOv8 model on a dataset of plant images to detect and classify diseases, evaluated through testing on both training and unseen images.

Potential Biases

Potential biases may arise from the dataset being limited to specific plant conditions.

Limitations

The model was trained on a limited range of plant diseases, which may affect its generalizability to other types.

Digital Object Identifier (DOI)

10.3390/pathogens13121032

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication