PlantTom: Balanced Tomato Leaf Disease Image Dataset for Object Detection

A revised dataset of 7,836 images representing 8 distinct tomato leaf disease classes, created by combining images from various public sources to address class imbalance. The dataset was developed by Vaskor Mostafa and last updated on 2026-05-22. It is intended for training and testing object detection models in smart agriculture applications.

Use Cases

• Training object detection models for tomato leaf disease identification based on the 8 distinct disease classes.
• Benchmarking model performance on a balanced dataset to mitigate class imbalance issues mentioned in the description.
• Developing deployable disease detection frameworks for smart agriculture based on the dataset's focus on precision and speed.
• Conducting ablation studies to evaluate the impact of specific neural network modules on detection accuracy.

Strengths

• 7,836 images providing a substantial base for model training.
• 8 distinct, balanced classes designed to reduce bias in performance evaluation.
• Dataset is explicitly revised to address common limitations like class imbalance found in public sources.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 5.5 KB, suggesting it may contain metadata or annotations rather than the image files themselves.

Provenance

Source

Combined from various public sources by author Vaskor Mostafa.

Collection Method

Images were aggregated from multiple public datasets to create a revised, balanced collection.

Time Range

null

Freshness

Last updated 2026-05-22 18:00:30; freshness should be verified.

Geography

null