Published August 15, 2024 | Version v1
Dataset Restricted

TomatoEbola dataset

Authors/Creators

  • 1. Victoria University of Wellington
  • 2. BRALN LTD

Contributors

  • 1. Victoria University of Wellington
  • 2. ROR icon University of Calabar

Description

The TomatoEbola dataset consists of images of tomato leaf diseases (both infected and healthy) collected from three farms in Yobe State, Nigeria: Dikumari, Kasaisa, and Kukareta wards. The dataset includes a total of 326 images, with 152 healthy and 174 infected. Specifically, Kasaisa contributes 122 images (52 healthy and 70 infected), Dikumari contributes 101 images (50 healthy and 51 infected), and Kukareta contributes 103 images (50 healthy and 53 infected).

Each farm's images are available in two formats: raw images and YOLOv8-labeled images. Some images contain multiple leaves, so bounding boxes are provided to accurately label each leaf. For detailed information on the number of images, total annotations, average annotations per image, image size, median image ratio, and the distribution of healthy and infected annotations,  refer to the list below. Researchers can also access the Roboflow project (link) to download the data in alternative labeling formats.

  1. Dikumari Farm
      - Images: 101
      - Average Annotations per Image: 2.1
      - Total Annotations: 217
      - Healthy Annotations: 117
      - Infected Annotations: 100
      - Image Size: 2.24 MP (Megapixels)
      - Image Dimensions: 1345 x 1673
  2. Kasaisa Farm
      - Images: 122
      - Average Annotations per Image: 2.6
      - Total Annotations: 319
      - Healthy Annotations: 138
      - Infected Annotations: 181
      - Image Size: 0.62 MP (Megapixels)
      - Image Dimensions: 667 x 906
  3. Kukareta Farm
      - Images: 103
      - Average Annotations per Image: 2.4
      - Total Annotations: 248
      - Healthy Annotations: 164
      - Infected Annotations: 84
      - Image Size: 0.87 MP (Megapixels)
      - Image Dimensions: 929 x 943

Files

Restricted

The record is publicly accessible, but files are restricted. <a href="https://zenodo.org/account/settings/login?next=https://zenodo.org/records/13324917">Log in</a> to check if you have access.

Additional details

Funding

Federal Government of Nigeria
Nigeria Artificial Intelligence Research Scheme NITDA/HQ/RG/AI5455239595

Software

Repository URL
https://github.com/harisushehu/Transformers-for-Tomato-Disease-Detection/tree/main
Programming language
Python
Development Status
Active

References

  • Shehu, H. A., Ackley, A., Mark, M., & Eteng, O. (2025). Early Detection of Tomato Leaf Diseases using Transformers and Transfer Learning. European Journal of Agronomy.
  • Shehu, H. A., Ackley, A., Mark, M., & Eteng, O. (2025). Artificial Intelligence for Early Detection and Management of Tomato Leaf Disease Caused by Tuta absoluta: A Systematic Review. European Journal of Agronomy.
  • Shehu, H. A., Ackley, A., Mark, M., & Eteng, O., Sharif, M.H., & Kusetogullari, H. (2025). YOLO for Early Detection and Management of Tuta absoluta Tomato Leaf Diseases. Frontiers in Plant Science.